{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:59:28Z","timestamp":1780779568297,"version":"3.54.1"},"reference-count":44,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems and Software"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.jss.2026.112930","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T09:52:37Z","timestamp":1778579557000},"page":"112930","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["OTBD: Overfitting tendency assessment based on benchmark deviation for dependable model training"],"prefix":"10.1016","volume":"240","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4241-1209","authenticated-orcid":false,"given":"Tao","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4791-5940","authenticated-orcid":false,"given":"Jun","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-6077","authenticated-orcid":false,"given":"Jingyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jss.2026.112930_b1","series-title":"2017 3rd IEEE International Conference on Cybernetics","first-page":"1","article-title":"SoftTarget regularization: An effective technique to reduce over-fitting in neural networks","author":"Aghajanyan","year":"2017"},{"key":"10.1016\/j.jss.2026.112930_b2","doi-asserted-by":"crossref","first-page":"29887","DOI":"10.1007\/s11042-022-12058-0","article-title":"Improvement of emotion recognition from facial images using deep learning and early stopping cross validation","volume":"81","author":"Bentoumi","year":"2022","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.jss.2026.112930_b3","unstructured":"Dinh, L., Pascanu, R., Bengio, S., Bengio, Y., 2017. Sharp minima can generalize for deep nets. In: Proceedings of the 34th International Conference on Machine Learning. ICML, Vol. 70, pp. 1019\u20131028."},{"key":"10.1016\/j.jss.2026.112930_b4","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.1007\/s00245-019-09591-0","article-title":"Approximation schemes for mixed optimal stopping and control problems with nonlinear expectations and jumps","volume":"83","author":"Dumitrescu","year":"2021","journal-title":"Appl. Math. Optim."},{"issue":"2","key":"10.1016\/j.jss.2026.112930_b5","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The PASCAL visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jss.2026.112930_b6","series-title":"Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation (GECCO05)","first-page":"1779","article-title":"Preventing overfitting in GP with canary functions","author":"Foreman","year":"2005"},{"key":"10.1016\/j.jss.2026.112930_b7","series-title":"Sharpness-Aware minimization for efficiently improving generalization","author":"Foret","year":"2020"},{"issue":"11","key":"10.1016\/j.jss.2026.112930_b8","first-page":"699","article-title":"DetectHATE: Detecting targeted hate - A framework for classifying online abuse on x","volume":"20","author":"Gashroo","year":"2024","journal-title":"Int. J. Perform. Eng."},{"issue":"11","key":"10.1016\/j.jss.2026.112930_b9","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: The KITTI dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.jss.2026.112930_b10","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"issue":"1","key":"10.1016\/j.jss.2026.112930_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/neco.1997.9.1.1","article-title":"Flat minima","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.jss.2026.112930_b12","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: Biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"10.1016\/j.jss.2026.112930_b13","first-page":"1","article-title":"Early stopping for iterative regularization with general loss functions","volume":"23","author":"Hu","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jss.2026.112930_b14","series-title":"Three factors influencing minima in SGD","author":"Jastrz\u0119bski","year":"2018"},{"key":"10.1016\/j.jss.2026.112930_b15","series-title":"Advances in Neural Information Processing Systems","first-page":"1805","article-title":"Early-stopped neural networks are consistent","author":"Ji","year":"2021"},{"issue":"3","key":"10.1016\/j.jss.2026.112930_b16","article-title":"Universal statistics of Fisher information in deep neural networks: Mean field approach","volume":"99","author":"Karakida","year":"2019","journal-title":"Phys. Rev. E"},{"key":"10.1016\/j.jss.2026.112930_b17","series-title":"International Conference on Learning Representations","article-title":"On Large-Batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2017"},{"key":"10.1016\/j.jss.2026.112930_b18","series-title":"YOLOv11: An overview of the key architectural enhancements","author":"Khanam","year":"2024"},{"key":"10.1016\/j.jss.2026.112930_b19","series-title":"Regularization for deep learning: A taxonomy","author":"Kuka\u010dka","year":"2017"},{"key":"10.1016\/j.jss.2026.112930_b20","doi-asserted-by":"crossref","first-page":"149","DOI":"10.14257\/ijmue.2014.9.8.13","article-title":"An adaptive stopping criterion for backpropagation learning in feedforward neural network","volume":"9","author":"Lalis","year":"2014","journal-title":"Int. J. Multimed. Ubiquitous Eng. (IJMUE)"},{"key":"10.1016\/j.jss.2026.112930_b21","series-title":"Advances in Neural Information Processing Systems","article-title":"Visualizing the loss landscape of neural nets","volume":"Vol. 31","author":"Li","year":"2018"},{"key":"10.1016\/j.jss.2026.112930_b22","first-page":"1","article-title":"Understanding generalization through progressive sharpening and edge-of-stability analysis","volume":"25","author":"Long","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jss.2026.112930_b23","series-title":"Learning sparse neural networks through L0 regularization","author":"Louizos","year":"2018"},{"key":"10.1016\/j.jss.2026.112930_b24","series-title":"How many factors influence minima in sgd?","author":"Luo","year":"2020"},{"issue":"2","key":"10.1016\/j.jss.2026.112930_b25","first-page":"65","article-title":"Modeling discourse for dialogue systems using spectral learning","volume":"21","author":"Mehndiratta","year":"2025","journal-title":"Int. J. Perform. Eng."},{"key":"10.1016\/j.jss.2026.112930_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127028","article-title":"Surpassing early stopping: A novel correlation-based stopping criterion for neural networks","volume":"567","author":"Miseta","year":"2024","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.jss.2026.112930_b27","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s41884-024-00142-3","article-title":"Feature learning and generalization error analysis of two-layer linear neural networks for high-dimensional inputs","volume":"8","author":"Nishimori","year":"2025","journal-title":"Inf. Geom."},{"key":"10.1016\/j.jss.2026.112930_b28","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/S0893-6080(98)00010-0","article-title":"Automatic early stopping using cross validation: quantifying the criteria","volume":"11","author":"Prechelt","year":"1998","journal-title":"Neural Netw."},{"key":"10.1016\/j.jss.2026.112930_b29","series-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering","first-page":"1008","article-title":"DeepArc: Modularizing neural networks for the model maintenance","author":"Ren","year":"2023"},{"key":"10.1016\/j.jss.2026.112930_b30","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1007\/s13389-024-00361-5","article-title":"Regularizers to the rescue: Fighting overfitting in deep learning-based side-channel analysis","volume":"14","author":"Rezaeezade","year":"2024","journal-title":"J. Cryptogr. Eng."},{"key":"10.1016\/j.jss.2026.112930_b31","doi-asserted-by":"crossref","first-page":"3106","DOI":"10.3390\/electronics12143106","article-title":"A review on dropout regularization approaches for deep neural networks within the scholarly domain","volume":"12","author":"Salehin","year":"2023","journal-title":"Electronics"},{"issue":"213","key":"10.1016\/j.jss.2026.112930_b32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3510413","article-title":"Avoiding overfitting: A survey on regularization methods for convolutional neural networks","volume":"54","author":"Santos","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.jss.2026.112930_b33","series-title":"On optimal early stopping: Over-informative versus under-informative parametrization","author":"Shen","year":"2022"},{"key":"10.1016\/j.jss.2026.112930_b34","series-title":"Optimal Stopping Rules","author":"Shiryaev","year":"2007"},{"key":"10.1016\/j.jss.2026.112930_b35","series-title":"Intelligent Computing","first-page":"218","article-title":"Deep feature discriminability as a diagnostic measure of overfitting in CNN models","author":"Sikha","year":"2024"},{"key":"10.1016\/j.jss.2026.112930_b36","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from Over-fitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jss.2026.112930_b37","series-title":"Recent Challenges in Intelligent Information and Database Systems","first-page":"175","article-title":"Gradient overdrive: Avoiding negative randomness effects in stochastic gradient descent","author":"Strzalka","year":"2024"},{"key":"10.1016\/j.jss.2026.112930_b38","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.jss.2026.112930_b39","series-title":"Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation","first-page":"877","article-title":"Measuring bloat, overfitting and functional complexity in genetic programming","author":"Vanneschi","year":"2010"},{"key":"10.1016\/j.jss.2026.112930_b40","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.neunet.2022.11.035","article-title":"Early stopping by correlating online indicators in neural networks","volume":"159","author":"Vilares Ferro","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.jss.2026.112930_b41","series-title":"Towards understanding generalization of deep learning: Perspective of loss landscapes","author":"Wu","year":"2017"},{"key":"10.1016\/j.jss.2026.112930_b42","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3974","article-title":"DOTA: A Large-Scale dataset for object detection in aerial images","author":"Xia","year":"2018"},{"key":"10.1016\/j.jss.2026.112930_b43","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s00365-006-0663-2","article-title":"On early stopping in gradient descent learning","volume":"26","author":"Yao","year":"2007","journal-title":"Constr. Approx."},{"key":"10.1016\/j.jss.2026.112930_b44","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.neunet.2021.12.016","article-title":"Fully corrective gradient boosting with squared hinge: Fast learning rates and early stopping","volume":"147","author":"Zeng","year":"2022","journal-title":"Neural Netw."}],"container-title":["Journal of Systems and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0164121226001639?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0164121226001639?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:23:46Z","timestamp":1780777426000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0164121226001639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":44,"alternative-id":["S0164121226001639"],"URL":"https:\/\/doi.org\/10.1016\/j.jss.2026.112930","relation":{},"ISSN":["0164-1212"],"issn-type":[{"value":"0164-1212","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OTBD: Overfitting tendency assessment based on benchmark deviation for dependable model training","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems and Software","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jss.2026.112930","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112930"}}