{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:21:00Z","timestamp":1783182060494,"version":"3.54.6"},"reference-count":76,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Fujian Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2022J011238"],"award-info":[{"award-number":["2022J011238"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133072","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T05:30:04Z","timestamp":1780119004000},"page":"133072","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Eliminating the optimization gap: A dual-temperature approach to supervised contrastive learning"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4525-2794","authenticated-orcid":false,"given":"Yifan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7964-173X","authenticated-orcid":false,"given":"Lei","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6298-846X","authenticated-orcid":false,"given":"Xia","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133072_bib0001","series-title":"Proceedings of the seventh international conference on learning representations","article-title":"Meta-learning with differentiable closed-form solvers","author":"Bertinetto","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0002","series-title":"Advances in neural information processing systems","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume":"vol. 32","author":"Cao","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0003","series-title":"Advances in neural information processing systems","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"vol. 33","author":"Caron","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0004","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0005","series-title":"Proceedings of the IEEE\/ACM 47th international conference on software engineering","first-page":"89","article-title":"Hedgecode: A multi-task hedging contrastive learning framework for code search","author":"Chen","year":"2025"},{"key":"10.1016\/j.eswa.2026.133072_bib0006","series-title":"Proceedings of the 37th international conference on machine learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"vol. 119","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0007","series-title":"Proceedings of the 16th European conference on computer vision","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0008","series-title":"Advances in neural information processing systems","first-page":"8765","article-title":"Debiased contrastive learning","volume":"vol. 33","author":"Chuang","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0009","series-title":"Proceedings of the 14th international conference on artificial intelligence and statistics","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"Coates","year":"2011"},{"key":"10.1016\/j.eswa.2026.133072_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","first-page":"702","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0011","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"715","article-title":"Parametric contrastive learning","author":"Cui","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9268","article-title":"Class-balanced loss based on effective number of samples","author":"Cui","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0013","series-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Human language technologies","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0014","series-title":"Proceedings of the ninth international conference on learning representations","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0015","series-title":"Proceedings of the 17th international conference on mining software repositories","first-page":"508","article-title":"A C\/C++ code vulnerability dataset with code changes and CVE summaries","author":"Fan","year":"2020"},{"issue":"4","key":"10.1016\/j.eswa.2026.133072_bib0016","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"Fei-Fei","year":"2006","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133072_bib0017","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.eswa.2026.133072_bib0018","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"6894","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","author":"Gao","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0019","series-title":"Advances in neural information processing systems","article-title":"Multi-level supervised contrastive learning","author":"Ghanooni","year":"2025"},{"key":"10.1016\/j.eswa.2026.133072_bib0020","series-title":"International conference on machine learning","first-page":"3821","article-title":"Dissecting supervised contrastive learning","author":"Graf","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0021","series-title":"Advances in neural information processing systems","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","volume":"vol. 33","author":"Grill","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0022","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (Volume 1: Long papers)","first-page":"7212","article-title":"UniXcoder: Unified cross-modal pre-training for code representation","author":"Guo","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0023","series-title":"Advances in neural information processing systems","first-page":"5000","article-title":"Provable guarantees for self-supervised deep learning with spectral contrastive loss","volume":"vol. 34","author":"HaoChen","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0025","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.133072_bib0026","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"5395","article-title":"Subclass-balancing contrastive learning for long-tailed recognition","author":"Hou","year":"2023"},{"key":"10.1016\/j.eswa.2026.133072_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128645","article-title":"A comprehensive survey on contrastive learning","volume":"610","author":"Hu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.133072_bib0028","series-title":"International conference on machine learning","first-page":"13774","article-title":"Model-aware contrastive learning: Towards escaping the dilemmas","author":"Huang","year":"2023"},{"issue":"330","key":"10.1016\/j.eswa.2026.133072_bib0029","first-page":"1","article-title":"The power of contrast for feature learning: A theoretical analysis","volume":"24","author":"Ji","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.133072_bib0030","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume":"vol. 139","author":"Jia","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0031","series-title":"Advances in neural information processing systems","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume":"vol. 33","author":"Kalantidis","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0032","series-title":"Proceedings of the eighth international conference on learning representations","article-title":"Decoupling representation and classifier for long-tailed recognition","author":"Kang","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0033","series-title":"Advances in neural information processing systems","first-page":"18661","article-title":"Supervised contrastive learning","volume":"vol. 33","author":"Khosla","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0034","series-title":"Technical Report","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.eswa.2026.133072_bib0035","unstructured":"Le, Y., & Yang, X. (2015). Tiny imagenet visual recognition challenge. CS231N course project report, Stanford University. https:\/\/cs231n.stanford.edu\/reports\/2015\/pdfs\/yle_project.pdf."},{"key":"10.1016\/j.eswa.2026.133072_bib0036","series-title":"Proceedings of the ninth international conference on learning representations","article-title":"Prototypical contrastive learning of unsupervised representations","author":"Li","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6918","article-title":"Targeted supervised contrastive learning for long-tailed recognition","author":"Li","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0038","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.eswa.2026.133072_bib0039","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019a). RoBERTa: A robustly optimized BERT pretraining approach. arXiv: 1907.11692."},{"key":"10.1016\/j.eswa.2026.133072_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2537","article-title":"Large-scale long-tailed recognition in an open world","author":"Liu","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0041","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.eswa.2026.133072_bib0042","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. Technical ReportarXiv: 1306.5151."},{"key":"10.1016\/j.eswa.2026.133072_bib0043","series-title":"NIPS workshop on deep learning and unsupervised feature learning","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"},{"key":"10.1016\/j.eswa.2026.133072_bib0044","series-title":"Proceedings of the Indian conference on computer vision, graphics and image processing","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"issue":"40","key":"10.1016\/j.eswa.2026.133072_bib0045","doi-asserted-by":"crossref","first-page":"24652","DOI":"10.1073\/pnas.2015509117","article-title":"Prevalence of neural collapse during the terminal phase of deep learning training","volume":"117","author":"Papyan","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.eswa.2026.133072_bib0046","series-title":"Proceedings of the 40th international conference on machine learning","first-page":"28389","article-title":"Not all semantics are created equal: Contrastive self-supervised learning with automatic temperature individualization","volume":"vol. 202","author":"Qiu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133072_bib0047","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0048","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"4512","article-title":"Making monolingual sentence embeddings multilingual using knowledge distillation","author":"Reimers","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0049","series-title":"International conference on machine learning","first-page":"19250","article-title":"Understanding contrastive learning requires incorporating inductive biases","author":"Saunshi","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0050","series-title":"International conference on machine learning","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"Saunshi","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0051","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"815","article-title":"FaceNet: A unified embedding for face recognition and clustering","author":"Schroff","year":"2015"},{"key":"10.1016\/j.eswa.2026.133072_bib0052","series-title":"Advances in neural information processing systems","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume":"vol. 29","author":"Sohn","year":"2016"},{"key":"10.1016\/j.eswa.2026.133072_bib0053","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6398","article-title":"Circle loss: A unified perspective of pair similarity optimization","author":"Sun","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0054","series-title":"Advances in neural information processing systems","first-page":"19511","article-title":"Understanding deep contrastive learning via coordinate-wise optimization","volume":"vol. 35","author":"Tian","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0055","series-title":"Proceedings of the 16th European conference on computer vision","first-page":"776","article-title":"Contrastive multiview coding","author":"Tian","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0056","series-title":"Advances in neural information processing systems","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"vol. 33","author":"Tian","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0057","series-title":"ICML 2018 workshop on theoretical foundations and applications of deep generative models","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"10.1016\/j.eswa.2026.133072_bib0058","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"8769","article-title":"The inaturalist species classification and detection dataset","author":"Van Horn","year":"2018"},{"key":"10.1016\/j.eswa.2026.133072_bib0059","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2495","article-title":"Understanding the behaviour of contrastive loss","author":"Wang","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0060","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"5265","article-title":"Cosface: Large margin cosine loss for deep face recognition","author":"Wang","year":"2018"},{"issue":"5","key":"10.1016\/j.eswa.2026.133072_bib0061","first-page":"5549","article-title":"Contrastive learning with stronger augmentations","volume":"45","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133072_bib0062","series-title":"Advances in neural information processing systems","article-title":"Variational supervised contrastive learning","author":"Wang","year":"2025"},{"issue":"5","key":"10.1016\/j.eswa.2026.133072_bib0063","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104211","article-title":"Grail: Graph contrastive learning with balanced negative sampling","volume":"62","author":"Xu","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.eswa.2026.133072_bib0064","series-title":"Advances in neural information processing systems","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"vol. 33","author":"You","year":"2020"},{"key":"10.1016\/j.eswa.2026.133072_bib0065","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6023","article-title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0066","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14441","article-title":"Dual temperature helps contrastive learning without many negative samples: Towards understanding and simplifying moco","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0067","series-title":"Proceedings of the sixth international conference on learning representations","article-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.eswa.2026.133072_bib0068","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"16786","article-title":"Multi-label supervised contrastive learning","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133072_bib0069","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2361","article-title":"Distribution alignment: A unified framework for long-tail visual recognition","author":"Zhang","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0070","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16660","article-title":"Use all the labels: A hierarchical multi-label contrastive learning framework","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0071","series-title":"Advances in neural information processing systems","article-title":"Character-level convolutional networks for text classification","volume":"vol. 28","author":"Zhang","year":"2015"},{"key":"10.1016\/j.eswa.2026.133072_bib0072","unstructured":"Zhong, Z., Cui, J., Li, Z., Lo, E., Sun, J., & Jia, J. (2022). Rebalanced siamese contrastive mining for long-tailed recognition. arXiv: 2203.11506."},{"key":"10.1016\/j.eswa.2026.133072_bib0073","series-title":"Advances in neural information processing systems","first-page":"10197","article-title":"Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks","volume":"vol. 32","author":"Zhou","year":"2019"},{"key":"10.1016\/j.eswa.2026.133072_bib0074","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6908","article-title":"Balanced contrastive learning for long-tailed visual recognition","author":"Zhu","year":"2022"},{"key":"10.1016\/j.eswa.2026.133072_bib0075","series-title":"Advances in neural information processing systems","first-page":"29820","article-title":"A geometric analysis of neural collapse with unconstrained features","volume":"vol. 34","author":"Zhu","year":"2021"},{"key":"10.1016\/j.eswa.2026.133072_bib0076","series-title":"Proceedings of the 38th international conference on machine learning","first-page":"12979","article-title":"Contrastive learning inverts the data generating process","volume":"vol. 139","author":"Zimmermann","year":"2021"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426019834?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426019834?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:03:47Z","timestamp":1783181027000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426019834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":76,"alternative-id":["S0957417426019834"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133072","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Eliminating the optimization gap: A dual-temperature approach to supervised contrastive learning","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133072","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133072"}}