{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T13:54:31Z","timestamp":1777125271373,"version":"3.51.4"},"reference-count":87,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172202"],"award-info":[{"award-number":["62172202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272221"],"award-info":[{"award-number":["62272221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572226"],"award-info":[{"award-number":["62572226"]}],"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":[[2026,7]]},"DOI":"10.1016\/j.scico.2026.103471","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T15:40:49Z","timestamp":1772984449000},"page":"103471","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Revealing unseen differences: A change metric perspective on deep learning software lifecycle for fine-tuning data debugging"],"prefix":"10.1016","volume":"252","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1884-7700","authenticated-orcid":false,"given":"Wenjie","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2282-7175","authenticated-orcid":false,"given":"Yanhui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4800-6255","authenticated-orcid":false,"given":"Mingliang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2352-2226","authenticated-orcid":false,"given":"Lin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4645-2526","authenticated-orcid":false,"given":"Yuming","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.scico.2026.103471_bib0001","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"10.1016\/j.scico.2026.103471_bib0002","series-title":"ICSE \u201920: 42nd International Conference on Software Engineering, Seoul, South Korea, 27 June - 19 July, 2020","first-page":"961","article-title":"Structure-invariant testing for machine translation","author":"He","year":"2020"},{"issue":"7553","key":"10.1016\/j.scico.2026.103471_bib0003","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"issue":"10210","key":"10.1016\/j.scico.2026.103471_bib0004","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.1016\/S0140-6736(19)32501-2","article-title":"Deep learning and medical diagnosis","volume":"394","author":"Liu","year":"2019","journal-title":"Lancet"},{"issue":"7","key":"10.1016\/j.scico.2026.103471_bib0005","doi-asserted-by":"crossref","first-page":"4316","DOI":"10.1109\/TITS.2020.3032227","article-title":"Deep learning for safe autonomous driving: current challenges and future directions","volume":"22","author":"Muhammad","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.scico.2026.103471_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2020.106384","article-title":"Deep learning for financial applications: a survey","volume":"93","author":"Ozbayoglu","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.scico.2026.103471_bib0007","series-title":"Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering","first-page":"1110","article-title":"Taxonomy of real faults in deep learning systems","author":"Humbatova","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0008","series-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE)","first-page":"385","article-title":"Measuring discrimination to boost comparative testing for multiple deep learning models","author":"Meng","year":"2021"},{"key":"10.1016\/j.scico.2026.103471_bib0009","series-title":"2019 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","first-page":"810","article-title":"An empirical study towards characterizing deep learning development and deployment across different frameworks and platforms","author":"Guo","year":"2019"},{"issue":"1","key":"10.1016\/j.scico.2026.103471_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TSE.2019.2962027","article-title":"Machine learning testing: survey, landscapes and horizons","volume":"48","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.scico.2026.103471_bib0011","first-page":"334","article-title":"Data validation for machine learning","volume":"1","author":"Polyzotis","year":"2019","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.scico.2026.103471_bib0012","series-title":"Proceedings of the 44th International Conference on Software Engineering","first-page":"573","article-title":"DeepFD: automated fault diagnosis and localization for deep learning programs","author":"Cao","year":"2022"},{"key":"10.1016\/j.scico.2026.103471_bib0013","series-title":"34th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2019, San Diego, CA, USA, November 11-15, 2019","first-page":"376","article-title":"Apricot: a weight-adaptation approach to fixing deep learning models","author":"Zhang","year":"2019"},{"issue":"2","key":"10.1016\/j.scico.2026.103471_bib0014","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MIS.2009.36","article-title":"The unreasonable effectiveness of data","volume":"24","author":"Halevy","year":"2009","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.scico.2026.103471_bib0015","series-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","first-page":"1","article-title":"\u201cEveryone wants to do the model work, not the data work\u201d: data cascades in high-stakes AI","author":"Sambasivan","year":"2021"},{"key":"10.1016\/j.scico.2026.103471_bib0016","doi-asserted-by":"crossref","unstructured":"O. Nahum, N. Calderon, O. Keller, I. Szpektor, R. Reichart, Are LLMs better than reported? Detecting label errors and mitigating their effect on model performance,(2024) arXiv: 2410.18889.","DOI":"10.18653\/v1\/2025.emnlp-main.1360"},{"issue":"8","key":"10.1016\/j.scico.2026.103471_bib0017","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1038\/s42256-022-00516-1","article-title":"Advances, challenges and opportunities in creating data for trustworthy AI","volume":"4","author":"Liang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.scico.2026.103471_bib0018","series-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"1345","article-title":"Dynamic data fault localization for deep neural networks","author":"Yin","year":"2023"},{"issue":"4","key":"10.1016\/j.scico.2026.103471_bib0019","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/MSPEC.2019.8678513","article-title":"IBM Watson, heal thyself: how IBM overpromised and underdelivered on AI health care","volume":"56","author":"Strickland","year":"2019","journal-title":"IEEE Spectr."},{"key":"10.1016\/j.scico.2026.103471_bib0020","series-title":"Proceedings of the 44th International Conference on Software Engineering","first-page":"2215","article-title":"Training data debugging for the fairness of machine learning software","author":"Li","year":"2022"},{"key":"10.1016\/j.scico.2026.103471_bib0021","series-title":"2019 IEEE\/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","first-page":"291","article-title":"Software engineering for machine learning: a case study","author":"Amershi","year":"2019"},{"issue":"4","key":"10.1016\/j.scico.2026.103471_bib0022","first-page":"1","article-title":"An empirical study on data distribution-aware test selection for deep learning enhancement","volume":"31","author":"Hu","year":"2022","journal-title":"ACM Trans. Softw. Eng. Methodol.)"},{"key":"10.1016\/j.scico.2026.103471_bib0023","series-title":"Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering","first-page":"1041","article-title":"Cats are not fish: deep learning testing calls for out-of-distribution awareness","author":"Berend","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0024","series-title":"Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering","first-page":"410","article-title":"Multiple-boundary clustering and prioritization to promote neural network retraining","author":"Shen","year":"2020"},{"issue":"8","key":"10.1016\/j.scico.2026.103471_bib0025","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/j.infsof.2005.07.001","article-title":"Towards a consistent terminology for software measurement","volume":"48","author":"Garc\u00eda","year":"2006","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.scico.2026.103471_bib0026","series-title":"Proceedings of the 30th International Conference on Software Engineering","first-page":"181","article-title":"A comparative analysis of the efficiency of change metrics and static code attributes for defect prediction","author":"Moser","year":"2008"},{"key":"10.1016\/j.scico.2026.103471_bib0027","series-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE)","first-page":"359","article-title":"Autotrainer: an automatic dnn training problem detection and repair system","author":"Zhang","year":"2021"},{"key":"10.1016\/j.scico.2026.103471_bib0028","series-title":"2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE)","first-page":"100","article-title":"Deepmutation: mutation testing of deep learning systems","author":"Ma","year":"2018"},{"key":"10.1016\/j.scico.2026.103471_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2020.106413","article-title":"Boundary sampling to boost mutation testing for deep learning models","volume":"130","author":"Shen","year":"2021","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.scico.2026.103471_bib0030","series-title":"Proceedings of the 27th ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"129","article-title":"An empirical study on tensorflow program bugs","author":"Zhang","year":"2018"},{"key":"10.1016\/j.scico.2026.103471_bib0031","series-title":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"510","article-title":"A comprehensive study on deep learning bug characteristics","author":"Islam","year":"2019"},{"key":"10.1016\/j.scico.2026.103471_bib0032","doi-asserted-by":"crossref","unstructured":"M.M. Morovati, A. Nikanjam, F. Tambon, F. Khomh, Z. Ming, et al., Bug characterization in machine learning-based systems, (2023)arXiv: 2307.14512.","DOI":"10.1007\/s10664-023-10400-0"},{"key":"10.1016\/j.scico.2026.103471_bib0033","series-title":"Database Systems for Advanced Applications: 25th International Conference, DASFAA 2020, Jeju, South Korea, September 24\u201327, 2020, Proceedings, Part I 25","first-page":"604","article-title":"An empirical study on bugs inside tensorflow","author":"Jia","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2021.110935","article-title":"The symptoms, causes, and repairs of bugs inside a deep learning library","volume":"177","author":"Jia","year":"2021","journal-title":"J. Syst. Softw."},{"issue":"6","key":"10.1016\/j.scico.2026.103471_bib0035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3587155","article-title":"Toward understanding deep learning framework bugs","volume":"32","author":"Chen","year":"2023","journal-title":"ACM Trans. Softw. Eng. Method."},{"key":"10.1016\/j.scico.2026.103471_bib0036","series-title":"2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE)","first-page":"251","article-title":"Deeplocalize: fault localization for deep neural networks","author":"Wardat","year":"2021"},{"key":"10.1016\/j.scico.2026.103471_bib0037","series-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","first-page":"1","article-title":"Umlaut: debugging deep learning programs using program structure and model behavior","author":"Schoop","year":"2021"},{"issue":"1","key":"10.1016\/j.scico.2026.103471_bib0038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3470006","article-title":"Automatic fault detection for deep learning programs using graph transformations","volume":"31","author":"Nikanjam","year":"2021","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"10.1016\/j.scico.2026.103471_bib0039","series-title":"Proceedings of the 44th International Conference on Software Engineering","first-page":"561","article-title":"DeepDiagnosis: automatically diagnosing faults and recommending actionable fixes in deep learning programs","author":"Wardat","year":"2022"},{"key":"10.1016\/j.scico.2026.103471_bib0040","unstructured":"M. Wardat, B.D. Cruz, W. Le, H. Rajan, An effective data-driven approach for localizing deep learning faults, (2023)arXiv: 2307.08947."},{"key":"10.1016\/j.scico.2026.103471_bib0041","series-title":"Proceedings of the 40th International Conference on Software Engineering","first-page":"303","article-title":"Deeptest: automated testing of deep-neural-network-driven autonomous cars","author":"Tian","year":"2018"},{"key":"10.1016\/j.scico.2026.103471_bib0042","series-title":"Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering","first-page":"132","article-title":"DeepRoad: GAN-based metamorphic testing and input validation framework for autonomous driving systems","author":"Zhang","year":"2018"},{"key":"10.1016\/j.scico.2026.103471_bib0043","series-title":"Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering","first-page":"347","article-title":"Deepbillboard: systematic physical-world testing of autonomous driving systems","author":"Zhou","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0044","series-title":"Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"480","article-title":"LiRTest: augmenting LiDAR point clouds for automated testing of autonomous driving systems","author":"Guo","year":"2022"},{"key":"10.1016\/j.scico.2026.103471_bib0045","series-title":"Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering","first-page":"974","article-title":"Automatic testing and improvement of machine translation","author":"Sun","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0046","series-title":"Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"863","article-title":"Machine translation testing via pathological invariance","author":"Gupta","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0047","series-title":"Proceedings of the 26th Symposium on Operating Systems Principles","first-page":"1","article-title":"Deepxplore: automated whitebox testing of deep learning systems","author":"Pei","year":"2017"},{"key":"10.1016\/j.scico.2026.103471_bib0048","series-title":"Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"146","article-title":"Deephunter: a coverage-guided fuzz testing framework for deep neural networks","author":"Xie","year":"2019"},{"key":"10.1016\/j.scico.2026.103471_bib0049","series-title":"Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"165","article-title":"Effective white-box testing of deep neural networks with adaptive neuron-selection strategy","author":"Lee","year":"2020"},{"key":"10.1016\/j.scico.2026.103471_bib0050","series-title":"Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"164","article-title":"BET: black-box efficient testing for convolutional neural networks","author":"Wang","year":"2022"},{"issue":"11","key":"10.1016\/j.scico.2026.103471_bib0051","doi-asserted-by":"crossref","first-page":"9185","DOI":"10.1109\/TNNLS.2022.3156620","article-title":"A white-box testing for deep neural networks based on neuron coverage","volume":"34","author":"Yu","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"10.1016\/j.scico.2026.103471_bib0052","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1109\/TSE.2007.70773","article-title":"Classifying software changes: clean or buggy?","volume":"34","author":"Kim","year":"2008","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.scico.2026.103471_bib0053","doi-asserted-by":"crossref","first-page":"19391","DOI":"10.1109\/ACCESS.2021.3054948","article-title":"Improving software defect prediction by aggregated change metrics","volume":"9","author":"\u0160iki\u0107","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.scico.2026.103471_bib0054","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.compeleceng.2018.02.043","article-title":"Empirical analysis of change metrics for software fault prediction","volume":"67","author":"Choudhary","year":"2018","journal-title":"Comput. Electr. Eng."},{"issue":"11","key":"10.1016\/j.scico.2026.103471_bib0055","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.scico.2026.103471_bib0056","unstructured":"A. Krizhevsky, G. Hinton, et al., Learning multiple layers of features from tiny images (2009) http:\/\/www.cs.utoronto.ca\/~kriz\/learning-features-2009-TR.pdf."},{"key":"10.1016\/j.scico.2026.103471_bib0057","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.scico.2026.103471_bib0058","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1016\/j.procs.2019.11.146","article-title":"Dealing with noise problem in machine learning data-sets: a systematic review","volume":"161","author":"Gupta","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.scico.2026.103471_bib0059","first-page":"770","article-title":"Amazon SageMaker debugger: a system for real-time insights into machine learning model training","volume":"3","author":"Rauschmayr","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.scico.2026.103471_bib0060","first-page":"89","article-title":"Sulla determinazione empirica di una legge didistribuzione","volume":"4","author":"An","year":"1933","journal-title":"Giorn Dell\u2019inst Ital Degli Att"},{"issue":"1","key":"10.1016\/j.scico.2026.103471_bib0061","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.scico.2026.103471_bib0062","series-title":"Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"67","article-title":"Deepcrime: mutation testing of deep learning systems based on real faults","author":"Humbatova","year":"2021"},{"key":"10.1016\/j.scico.2026.103471_bib0063","series-title":"2020 IEEE 13th International Conference on Software Testing, Validation and Verification (ICST)","first-page":"74","article-title":"An empirical evaluation of mutation operators for deep learning systems","author":"Jahangirova","year":"2020"},{"issue":"3","key":"10.1016\/j.scico.2026.103471_bib0064","first-page":"370","article-title":"Generalized linear models","volume":"135","author":"Nelder","year":"1972","journal-title":"J. R. Stat. Soc. Ser. A Stat. Soc."},{"key":"10.1016\/j.scico.2026.103471_bib0065","doi-asserted-by":"crossref","unstructured":"J. Cohen, A power primer. Psychol. Bull. 112 (1992) 155\u2013159.","DOI":"10.1037\/0033-2909.112.1.155"},{"key":"10.1016\/j.scico.2026.103471_bib0066","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1022643204877","article-title":"Induction of decision trees","volume":"1","author":"Quinlan","year":"1986","journal-title":"Mach. Learn."},{"key":"10.1016\/j.scico.2026.103471_bib0067","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"issue":"1","key":"10.1016\/j.scico.2026.103471_bib0068","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10.1016\/j.scico.2026.103471_bib0069","unstructured":"scikit-learn, Decision Trees, 2025, https:\/\/scikit-learn.org\/stable\/modules\/tree.html."},{"key":"10.1016\/j.scico.2026.103471_bib0070","unstructured":"W. contributors, Random forest \u2013 Wikipedia, The Free Encyclopedia, 2025, [Online; accessed 26-February-2025], https:\/\/en.wikipedia.org\/wiki\/Random_forest."},{"key":"10.1016\/j.scico.2026.103471_bib0071","unstructured":"Wikipedia contributors, Naive Bayes classifier \u2013 Wikipedia, the free encyclopedia, 2025a, (2025a). [Online; accessed 26-February-2025], https:\/\/en.wikipedia.org\/wiki\/Naive_Bayes_classifier."},{"key":"10.1016\/j.scico.2026.103471_bib0072","unstructured":"Wikipedia contributors, K-nearest neighbors algorithm \u2014 Wikipedia, the free encyclopedia, 2025b, (2025b). [Online; accessed 26-February-2025], https:\/\/en.wikipedia.org\/wiki\/K-nearest_neighbors_algorithm."},{"key":"10.1016\/j.scico.2026.103471_bib0073","unstructured":"scikit-learn, Linear models, 2025a, https:\/\/scikit-learn.org\/stable\/modules\/linear_model.html#logistic-regression."},{"key":"10.1016\/j.scico.2026.103471_bib0074","unstructured":"scikit-learn, Sklearn, make circles dataset, 2025b, (2025b). https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.datasets.make_circles.html."},{"key":"10.1016\/j.scico.2026.103471_bib0075","unstructured":"scikit-learn, Sklearn, make blobs dataset, 2025c, (2025c). https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.datasets.make_blobs.html."},{"key":"10.1016\/j.scico.2026.103471_bib0076","unstructured":"Y. LeCun, C. Corinna, MNIST handwritten digit database, 2010, (2010). http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"10.1016\/j.scico.2026.103471_bib0077","series-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"Maas","year":"2011"},{"key":"10.1016\/j.scico.2026.103471_bib0078","unstructured":"D. Lewis, Reuters-21578 text categorization collection, 1997, (UCI Machine Learning Repository). 10.24432\/C52G6M."},{"key":"10.1016\/j.scico.2026.103471_bib0079","unstructured":"scikit-learn, machine learning in python, 2025, https:\/\/scikit-learn.org\/stable\/."},{"key":"10.1016\/j.scico.2026.103471_bib0080","series-title":"Breakthroughs in Statistics: Methodology and Distribution","first-page":"196","article-title":"Individual comparisons by ranking methods","author":"Wilcoxon","year":"1992"},{"key":"10.1016\/j.scico.2026.103471_bib0081","series-title":"Annual Meeting of the Southern Association for Institutional Research","article-title":"Exploring methods for evaluating group differences on the NSSE and other surveys: are the t-test and Cohen\u2019s d indices the most appropriate choices","author":"Romano","year":"2006"},{"key":"10.1016\/j.scico.2026.103471_bib0082","series-title":"Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering","first-page":"508","article-title":"Heterogeneous defect prediction","author":"Nam","year":"2015"},{"key":"10.1016\/j.scico.2026.103471_bib0083","series-title":"2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER)","first-page":"232","article-title":"Connecting software metrics across versions to predict defects","author":"Liu","year":"2018"},{"key":"10.1016\/j.scico.2026.103471_bib0084","series-title":"2009 IEEE\/ACM International Conference on Automated Software Engineering","first-page":"600","article-title":"Reducing features to improve bug prediction","author":"Shivaji","year":"2009"},{"issue":"3","key":"10.1016\/j.scico.2026.103471_bib0085","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/TSE.2011.20","article-title":"Which crashes should i fix first?: predicting top crashes at an early stage to prioritize debugging efforts","volume":"37","author":"Kim","year":"2011","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"11","key":"10.1016\/j.scico.2026.103471_bib0086","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1109\/TSE.2016.2550458","article-title":"Developer micro interaction metrics for software defect prediction","volume":"42","author":"Lee","year":"2016","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.scico.2026.103471_bib0087","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.infsof.2018.10.004","article-title":"Software defect prediction based on kernel PCA and weighted extreme learning machine","volume":"106","author":"Xu","year":"2019","journal-title":"Inf. Softw. Technol."}],"container-title":["Science of Computer Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167642326000377?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167642326000377?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T13:29:49Z","timestamp":1777123789000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167642326000377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":87,"alternative-id":["S0167642326000377"],"URL":"https:\/\/doi.org\/10.1016\/j.scico.2026.103471","relation":{},"ISSN":["0167-6423"],"issn-type":[{"value":"0167-6423","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Revealing unseen differences: A change metric perspective on deep learning software lifecycle for fine-tuning data debugging","name":"articletitle","label":"Article Title"},{"value":"Science of Computer Programming","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.scico.2026.103471","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":"103471"}}