{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:53:14Z","timestamp":1782222794518,"version":"3.54.5"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472138"],"award-info":[{"award-number":["62472138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Continual Learning (CL), involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation\u2013based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their ability to distill the cumulative knowledge of all the previous tasks. To remedy this, we propose Random Dense Knowledge Distillation (RDKD). RDKD uses a task pool to track the model\u2019s capabilities. It partitions the output logits of the model into dense groups, each corresponding to a task in the task pool. It then distills all tasks\u2019 knowledge using all groups. However, using all the groups can be computationally expensive, so we also suggest random group selection in each optimization step. Moreover, we propose an adaptive weighting scheme, which balances the learning of new classes and the retention of old classes, based on the count and similarity of the classes. Our RDKD outperforms recent state-of-the-art baselines across diverse benchmarks and scenarios. Empirical analysis underscores RDKD\u2019s ability to enhance model stability, promotes flatter minima for improved generalization, and remains robust across various memory budgets and task orders. Moreover, it seamlessly integrates with other CL methods to boost performance and proves versatile in offline scenarios like model compression.<\/jats:p>","DOI":"10.1145\/3816731","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:59:29Z","timestamp":1779890369000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Random Dense Knowledge Distillation for Continual Learning"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7672-6134","authenticated-orcid":false,"given":"Jie","family":"Chu","sequence":"first","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6044-5317","authenticated-orcid":false,"given":"Pei","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1386-8511","authenticated-orcid":false,"given":"Tong","family":"Su","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0648-868X","authenticated-orcid":false,"given":"Yunpeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0771-7499","authenticated-orcid":false,"given":"Yu","family":"Song","sequence":"additional","affiliation":[{"name":"Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-1409","authenticated-orcid":false,"given":"Zenglin","family":"Shi","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01151"},{"key":"e_1_3_1_5_2","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Aljundi Rahaf","year":"2019","unstructured":"Rahaf Aljundi, Min Lin, Baptiste Goujaud, and Yoshua Bengio. 2019. Gradient based sample selection for online continual learning. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_1_6_2","unstructured":"Ibtihel Amara Maryam Ziaeefard Brett H. Meyer Warren Gross and James J. Clark. 2022. CES-KD: Curriculum-based expert selection for guided knowledge distillation. arXiv220907606. Retrieved from https:\/\/arxiv.org\/abs\/2209.07606"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564786"},{"key":"e_1_3_1_9_2","unstructured":"Risab Biswas. 2024. Multi-task multi-scale contrastive knowledge distillation for efficient medical image segmentation. arXiv240603173. Retrieved from https:\/\/arxiv.org\/abs\/2406.03173"},{"key":"e_1_3_1_10_2","volume-title":"NeurIPS","author":"Buzzega Pietro","year":"2020","unstructured":"Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, and Simone Calderara. 2020. Dark experience for general continual learning: A strong, simple baseline. In NeurIPS."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","first-page":"23724","DOI":"10.1609\/aaai.v39i22.34543","article-title":"Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models","volume":"39","author":"Cui Xiao","year":"2025","unstructured":"Xiao Cui, Mo Zhu, Yulei Qin, Liang Xie, Wengang Zhou, and Houqiang Li. 2025. Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models. Proceedings of the AAAI Conference on Artificial Intelligence 39 (2025), 23724\u201323732.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"issue":"55","key":"e_1_3_1_16_2","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"Elsken Thomas","year":"2019","unstructured":"Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. 2019. Neural architecture search: A survey. Journal of Machine Learning Research 20, 55 (2019), 1\u201321.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"e_1_3_1_17_2","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10462-025-11423-3","article-title":"Knowledge distillation and dataset distillation of large language models: Emerging trends, challenges, and future directions","volume":"59","author":"Fang Luyang","year":"2026","unstructured":"Luyang Fang, Xiaowei Yu, Jiazhang Cai, Yongkai Chen, Shushan Wu, Zhengliang Liu, Zhenyuan Yang, Haoran Lu, Xilin Gong, Yufang Liu, et al. 2026. Knowledge distillation and dataset distillation of large language models: Emerging trends, challenges, and future directions. Artificial Intelligence Review 59, 1 (2026), 17.","journal-title":"Artificial Intelligence Review"},{"key":"e_1_3_1_18_2","volume-title":"ECCV","author":"Gao Qiankun","year":"2022","unstructured":"Qiankun Gao, Chen Zhao, Bernard Ghanem, and Jian Zhang. 2022. R-DFCIL: Relation-guided representation learning for data-free class incremental learning. In ECCV."},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Zhi Gao Chen Xu Feng Li Yunde Jia Mehrtash Harandi and Yuwei Wu. 2023. Exploring data geometry for continual learning. arXiv:2304.03931. Retrieved from https:\/\/arxiv.org\/abs\/2304.03931","DOI":"10.1109\/CVPR52729.2023.02330"},{"key":"e_1_3_1_20_2","unstructured":"Ian J. Goodfellow Mehdi Mirza Da Xiao Aaron Courville and Yoshua Bengio. 2013. An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv:1312.6211. Retrieved from https:\/\/arxiv.org\/abs\/1312.6211"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_1_22_2","unstructured":"Shivam Gupta and Sushrut Karmalkar. 2025. Efficient knowledge distillation via curriculum extraction. arXiv:2503.17494. Retrieved from https:\/\/arxiv.org\/abs\/2503.17494"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102742"},{"key":"e_1_3_1_24_2","unstructured":"Geoffrey Hinton Oriol Vinyals Jeff Dean et al. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_27"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00395"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01141"},{"key":"e_1_3_1_29_2","volume-title":"NeurIPS","author":"Hung Ching-Yi","year":"2019","unstructured":"Ching-Yi Hung, Cheng-Hao Tu, Cheng-En Wu, Chien Hung Chen, Yi-Ming Chan, and Chu-Song Chen. 2019. Compacting, picking and growing for unforgetting continual learning. In NeurIPS."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"e_1_3_1_31_2","unstructured":"Persia Jana Kamali and Pierfrancesco Urbani. 2023. Stochastic gradient descent outperforms gradient descent in recovering a high-dimensional signal in a glassy energy landscape. arXiv:2309.04788. Retrieved from https:\/\/arxiv.org\/abs\/2309.04788"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01560"},{"key":"e_1_3_1_33_2","unstructured":"Seongjae Kang Dong Bok Lee Hyungjoon Jang and Sung Ju Hwang. 2025. Simple yet effective semi-supervised knowledge distillation from vision-language models via dual-head optimization. arXiv:2505.07675. Retrieved from https:\/\/arxiv.org\/abs\/2505.07675"},{"key":"e_1_3_1_34_2","volume-title":"CVPR","author":"Kim Dongwan","year":"2023","unstructured":"Dongwan Kim and Bohyung Han. 2023. On the stability-plasticity dilemma of class-incremental learning. In CVPR."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_1_36_2","volume-title":"CVPR","author":"Lee Janghyeon","year":"2020","unstructured":"Janghyeon Lee, Hyeong Gwon Hong, Donggyu Joo, and Junmo Kim. 2020. Continual learning with extended Kronecker-factored approximate curvature. In CVPR."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00040"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3476068"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3604362"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576045"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICVRV67992.2025.00097"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICVRV67992.2025.00096"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"e_1_3_1_45_2","unstructured":"Amir M. Mansourian Rozhan Ahmadi Masoud Ghafouri Amir Mohammad Babaei Elaheh Badali Golezani Zeynab Yasamani Ghamchi Vida Ramezanian Alireza Taherian Kimia Dinashi Amirali Miri et al. 2025. A comprehensive survey on knowledge distillation. arXiv:2503.12067. Retrieved from https:\/\/arxiv.org\/abs\/2503.12067"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617833"},{"key":"e_1_3_1_47_2","first-page":"109","volume-title":"Psychology of Learning and Motivation","author":"McCloskey Michael","year":"1989","unstructured":"Michael McCloskey and Neal J. Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of Learning and Motivation. Gordon H. Bower (Ed.), Vol. 24. Elsevier, 109\u2013165. Retrieved from https:\/\/www.sciencedirect.com\/bookseries\/psychology-of-learning-and-motivation\/vol\/24\/suppl\/C"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00390"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01392-1"},{"key":"e_1_3_1_51_2","first-page":"16131","volume-title":"NeurIPS","author":"Pham Quang","year":"2021","unstructured":"Quang Pham, Chenghao Liu, and Steven Hoi. 2021. DualNet: Continual learning, fast and slow. In NeurIPS, 16131\u201316144."},{"key":"e_1_3_1_52_2","volume-title":"NeurIPS","author":"Rajasegaran Jathushan","year":"2019","unstructured":"Jathushan Rajasegaran, Munawar Hayat, Salman H. Khan, Fahad Shahbaz Khan, and Ling Shao. 2019. Random path selection for continual learning. In NeurIPS."},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.97.2.285"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"e_1_3_1_56_2","volume-title":"NeruIPS","volume":"32","author":"Rolnick David","year":"2019","unstructured":"David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, and Gregory Wayne. 2019. Experience replay for continual learning. In NeruIPS, Vol. 32."},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_1_58_2","volume-title":"ICML","author":"Schwarz Jonathan","year":"2018","unstructured":"Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, and Raia Hadsell. 2018. Progress & compress: A scalable framework for continual learning. In ICML."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3687128"},{"key":"e_1_3_1_60_2","unstructured":"Zenglin Shi Tong Su Pei Liu Yunpeng Wu Le Zhang and Meng Wang. 2024. Learning frequency-aware dynamic transformers for all-in-one image restoration. arXiv:2407.01636. Retrieved from https:\/\/arxiv.org\/abs\/2407.01636"},{"key":"e_1_3_1_61_2","volume-title":"CVPR","author":"Simon Christian","year":"2021","unstructured":"Christian Simon, Piotr Koniusz, and Mehrtash Harandi. 2021. On learning the geodesic path for incremental learning. In CVPR."},{"key":"e_1_3_1_62_2","unstructured":"James Seale Smith Leonid Karlinsky Vyshnavi Gutta Paola Cascante-Bonilla Donghyun Kim Assaf Arbelle Rameswar Panda Rogerio Feris and Zsolt Kira. 2023. CODA-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. arXiv:2211.13218. Retrieved from https:\/\/arxiv.org\/abs\/2211.13218"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14193891"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106163"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_16"},{"key":"e_1_3_1_66_2","unstructured":"Gido M. Van de Ven and Andreas S. Tolias. 2019. Three scenarios for continual learning. arXiv:1904.07734. Retrieved from https:\/\/arxiv.org\/abs\/1904.07734"},{"key":"e_1_3_1_67_2","volume-title":"ECCV","author":"Wang Fu-Yun","year":"2022","unstructured":"Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. 2022. Foster: Feature boosting and compression for class-incremental learning. In ECCV."},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"e_1_3_1_69_2","doi-asserted-by":"crossref","unstructured":"Zifeng Wang Zizhao Zhang Sayna Ebrahimi Ruoxi Sun Han Zhang Chen-Yu Lee Xiaoqi Ren Guolong Su Vincent Perot Jennifer Dy et al. 2022. DualPrompt: Complementary prompting for rehearsal-free continual learning. arXiv:2204.04799. Retrieved from https:\/\/arxiv.org\/abs\/2204.04799","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"e_1_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Zifeng Wang Zizhao Zhang Chen-Yu Lee Han Zhang Ruoxi Sun Xiaoqi Ren Guolong Su Vincent Perot Jennifer Dy and Tomas Pfister. 2022. Learning to prompt for continual learning. arXiv:2112.08654. Retrieved from https:\/\/arxiv.org\/abs\/2112.08654","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553517"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_3_1_73_2","volume-title":"NeurIPS","author":"Xu Ju","year":"2018","unstructured":"Ju Xu and Zhanxing Zhu. 2018. Reinforced continual learning. In NeurIPS."},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591209"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3661312"},{"key":"e_1_3_1_77_2","unstructured":"Jaehong Yoon Eunho Yang Jeongtae Lee and Sung Ju Hwang. 2017. Lifelong learning with dynamically expandable networks. arXiv:1708.01547. Retrieved from https:\/\/arxiv.org\/abs\/1708.01547"},{"key":"e_1_3_1_78_2","volume-title":"ICML","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In ICML."},{"key":"e_1_3_1_79_2","volume-title":"WACV","author":"Zhang Junting","year":"2020","unstructured":"Junting Zhang, Jie Zhang, Shalini Ghosh, Dawei Li, Serafettin Tasci, Larry Heck, Heming Zhang, and C.-C. Jay Kuo. 2020. Class-incremental learning via deep model consolidation. In WACV."},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3133897"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01473-9"},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429383"},{"key":"e_1_3_1_83_2","unstructured":"Da-Wei Zhou Qi-Wei Wang Han-Jia Ye and De-Chuan Zhan. 2022. A model or 603 exemplars: Towards memory-efficient class-incremental learning. arXiv:2205.13218. Retrieved from https:\/\/arxiv.org\/abs\/2205.13218"},{"key":"e_1_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889653"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3816731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:14:09Z","timestamp":1782220449000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3816731"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":83,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3816731"],"URL":"https:\/\/doi.org\/10.1145\/3816731","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"2025-09-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}