{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:49:01Z","timestamp":1785908941070,"version":"3.56.0"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010226","name":"Department of Education of Guangdong Province","doi-asserted-by":"publisher","award":["2020KCXTD014"],"award-info":[{"award-number":["2020KCXTD014"]}],"id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012653"],"award-info":[{"award-number":["2023A1515012653"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2026A1515011903"],"award-info":[{"award-number":["2026A1515011903"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62576115"],"award-info":[{"award-number":["62576115"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Science of Computer Programming"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.scico.2026.103523","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T17:24:32Z","timestamp":1781457872000},"page":"103523","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Explainability-guided augmentation for data-scarce CPDP via semantic anchors"],"prefix":"10.1016","volume":"254","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4736-1845","authenticated-orcid":false,"given":"Yongchang","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haihao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunkun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Lihaosheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Yuan","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.scico.2026.103523_bib0001","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10515-024-00424-1","article-title":"Software defect prediction: future directions and challenges","volume":"31","author":"Li","year":"2024","journal-title":"Autom. Softw. Eng."},{"issue":"1","key":"10.1016\/j.scico.2026.103523_bib0002","first-page":"44","article-title":"On the multiple sources and privacy preservation issues for heterogeneous defect prediction","volume":"44","author":"Li","year":"2017","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"5","key":"10.1016\/j.scico.2026.103523_bib0003","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1007\/s10664-008-9103-7","article-title":"On the relative value of cross-company and within-company data for defect prediction","volume":"14","author":"Turhan","year":"2009","journal-title":"Empir. Softw. Eng."},{"key":"10.1016\/j.scico.2026.103523_bib0004","series-title":"Proceedings of the 30th IEEE\/ACM International Conference on Automated Software Engineering","first-page":"452","article-title":"CLAMI: Defect prediction on unlabeled datasets (T)","author":"Nam","year":"2015"},{"key":"10.1016\/j.scico.2026.103523_bib0005","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.infsof.2018.04.001","article-title":"Cross project defect prediction using class distribution estimation and oversampling","volume":"100","author":"Limsettho","year":"2018","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.scico.2026.103523_bib0006","article-title":"Metric information mining with metric attention to boost software defect prediction performance","volume":"248","author":"Ding","year":"2025","journal-title":"Sci. Comput. Program."},{"key":"10.1016\/j.scico.2026.103523_bib0007","series-title":"Proceedings of the 10th Joint Meeting on Foundations of Software Engineering","first-page":"391","article-title":"Heterogeneous cross-company defect prediction by unified metric representation and CCA-based transfer learning","author":"Jing","year":"2015"},{"issue":"1","key":"10.1016\/j.scico.2026.103523_bib0008","first-page":"200","article-title":"Unsupervised cross-project defect prediction via landmark selection and manifold learning","volume":"74","author":"Li","year":"2025","journal-title":"IEEE Trans. Reliab."},{"issue":"6","key":"10.1016\/j.scico.2026.103523_bib0009","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1007\/s10489-025-06288-6","article-title":"Multi-view learning based on product and process metrics for software defect prediction: Y. Sun et al","volume":"55","author":"Sun","year":"2025","journal-title":"Appl. Intell."},{"issue":"1","key":"10.1016\/j.scico.2026.103523_bib0010","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s10515-016-0194-x","article-title":"Label propagation based semi-supervised learning for software defect prediction","volume":"24","author":"Zhang","year":"2017","journal-title":"Autom. Softw. Eng."},{"key":"10.1016\/j.scico.2026.103523_bib0011","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.scico.2026.103523_bib0012","series-title":"Advances in Intelligent Computing","first-page":"878","article-title":"Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning","author":"Han","year":"2005"},{"key":"10.1016\/j.scico.2026.103523_bib0013","series-title":"2008 IEEE International Joint Conference on Neural Networks (IJCNN)","first-page":"1322","article-title":"ADASYN: adaptive synthetic sampling approach for imbalanced learning","author":"He","year":"2008"},{"key":"10.1016\/j.scico.2026.103523_bib0014","series-title":"International Conference on Intelligent Data Engineering and Automated Learning","first-page":"431","article-title":"Enhanced svm-smote with cluster consistency for imbalanced data classification","author":"Miftahushudur","year":"2023"},{"key":"10.1016\/j.scico.2026.103523_bib0015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ins.2018.06.056","article-title":"Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE","volume":"465","author":"Douzas","year":"2018","journal-title":"Inf. Sci."},{"issue":"6","key":"10.1016\/j.scico.2026.103523_bib0016","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1109\/TSE.2017.2731766","article-title":"Mahakil: diversity based oversampling approach to alleviate the class imbalance issue in software defect prediction","volume":"44","author":"Bennin","year":"2017","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"3","key":"10.1016\/j.scico.2026.103523_bib0017","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1109\/TSMC.1972.4309137","article-title":"Asymptotic properties of nearest neighbor rules using edited data","volume":"SMC-2","author":"Wilson","year":"1972","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"1","key":"10.1016\/j.scico.2026.103523_bib0018","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/1007730.1007735","article-title":"A study of the behavior of several methods for balancing machine learning training data","volume":"6","author":"Batista","year":"2004","journal-title":"SIGKDD Explor. Newsl."},{"key":"10.1016\/j.scico.2026.103523_bib0019","series-title":"Proceedings of Workshop on Learning from Imbalanced Datasets","first-page":"1","article-title":"kNN approach to unbalanced data distributions: a case study involving information extraction","volume":"Vol. 126","author":"Mani","year":"2003"},{"key":"10.1016\/j.scico.2026.103523_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2020.106432","article-title":"COSTE: complexity-based oversampling technique to alleviate the class imbalance problem in software defect prediction","volume":"129","author":"Feng","year":"2021","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.scico.2026.103523_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121053","article-title":"Geometric SMOTE for imbalanced datasets with nominal and continuous features","volume":"234","author":"Fonseca","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.scico.2026.103523_bib0022","series-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"1135","article-title":"\u201c Why should i trust you?\u201d Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"10.1016\/j.scico.2026.103523_bib0023","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"1287","article-title":"Explaining the explainer: a first theoretical analysis of LIME","author":"Garreau","year":"2020"},{"key":"10.1016\/j.scico.2026.103523_bib0024","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"Vol. 30","author":"Lundberg","year":"2017"},{"key":"10.1016\/j.scico.2026.103523_bib0025","series-title":"2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","first-page":"179","article-title":"An empirical comparison of model-agnostic techniques for defect prediction models","author":"Lee","year":"2023"},{"issue":"4","key":"10.1016\/j.scico.2026.103523_bib0026","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/s10664-024-10469-1","article-title":"Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP","volume":"29","author":"Schulte","year":"2024","journal-title":"Empir. Softw. Eng."},{"key":"10.1016\/j.scico.2026.103523_bib0027","article-title":"A joint learning framework for bridging defect prediction and interpretation","author":"Xu","year":"2025","journal-title":"IEEE Trans. Reliab."},{"key":"10.1016\/j.scico.2026.103523_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2024.112182","article-title":"CfExplainer: explainable just-in-time defect prediction based on counterfactuals","volume":"218","author":"Yang","year":"2024","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.scico.2026.103523_bib0029","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1016\/j.ins.2023.03.038","article-title":"A supervised data augmentation strategy based on random combinations of key features","volume":"632","author":"Ding","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.scico.2026.103523_bib0030","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"1536","article-title":"CodeBERT: a pre-trained model for programming and natural languages","author":"Feng","year":"2020"},{"key":"10.1016\/j.scico.2026.103523_bib0031","series-title":"International Conference on Biomedical and Intelligent Systems (IC-BIS 2022)","first-page":"402","article-title":"Research on random forest drug classification prediction model based on KMeans-SMOTE","volume":"Vol. 12458","author":"Song","year":"2022"},{"key":"10.1016\/j.scico.2026.103523_bib0032","series-title":"2018 IEEE International Conference on Information Reuse and Integration (IRI)","first-page":"70","article-title":"The effects of random undersampling with simulated class imbalance for big data","author":"Hasanin","year":"2018"},{"issue":"3","key":"10.1016\/j.scico.2026.103523_bib0033","first-page":"345","article-title":"A hybrid sampling approach for improving the classification of imbalanced data using ROS and NCL methods","volume":"16","author":"Ependi","year":"2023","journal-title":"Int. J. Intell. Eng. Syst."},{"issue":"5","key":"10.1016\/j.scico.2026.103523_bib0034","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1007\/s11390-019-1959-z","article-title":"Cross project defect prediction via balanced distribution adaptation based transfer learning","volume":"34","author":"Xu","year":"2019","journal-title":"J. Comput. Sci. Technol."},{"issue":"4","key":"10.1016\/j.scico.2026.103523_bib0035","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1109\/TSE.2022.3204589","article-title":"Dssdpp: data selection and sampling based domain programming predictor for cross-project defect prediction","volume":"49","author":"Li","year":"2022","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"2","key":"10.1016\/j.scico.2026.103523_bib0036","first-page":"500","article-title":"Cross-project defect prediction via landmark selection-based kernelized discriminant subspace learning","volume":"70","author":"Li","year":"2021","journal-title":"IEEE Trans. Reliab."},{"key":"10.1016\/j.scico.2026.103523_bib0037","series-title":"Intelligent Software Defect Prediction","first-page":"35","article-title":"Cross-project defect prediction","author":"Jing","year":"2024"},{"issue":"2","key":"10.1016\/j.scico.2026.103523_bib0038","doi-asserted-by":"crossref","DOI":"10.20473\/jisebi.9.2.228-238","article-title":"Transfer learning based low shot classifier for software defect prediction","volume":"9","author":"Suhag","year":"2023","journal-title":"J. Inf. Syst. Eng. Bus. Intell."},{"key":"10.1016\/j.scico.2026.103523_bib0039","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"7335","article-title":"Modeling tabular data using conditional GAN","volume":"Vol. 32","author":"Xu","year":"2019"},{"key":"10.1016\/j.scico.2026.103523_bib0040","series-title":"2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","first-page":"399","article-title":"The synthetic data vault","author":"Patki","year":"2016"},{"key":"10.1016\/j.scico.2026.103523_bib0041","series-title":"Advances in Neural Information Processing Systems","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume":"Vol. 30","author":"Snell","year":"2017"},{"key":"10.1016\/j.scico.2026.103523_bib0042","series-title":"Annual Meeting of the Florida Association of Institutional Research","article-title":"Appropriate statistics for ordinal level data: should we really be using t-test and Cohen\u2019s d?","author":"Romano","year":"2006"}],"container-title":["Science of Computer Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167642326000894?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167642326000894?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:20:02Z","timestamp":1785907202000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167642326000894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":42,"alternative-id":["S0167642326000894"],"URL":"https:\/\/doi.org\/10.1016\/j.scico.2026.103523","relation":{},"ISSN":["0167-6423"],"issn-type":[{"value":"0167-6423","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Explainability-guided augmentation for data-scarce CPDP via semantic anchors","name":"articletitle","label":"Article Title"},{"value":"Science of Computer Programming","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.scico.2026.103523","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103523"}}