{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:58:00Z","timestamp":1777694280794,"version":"3.51.4"},"reference-count":96,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Integrated Computer-Aided Engineering"],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:p>Distributed Machine learning has delivered considerable advances in training neural networks by leveraging parallel processing, scalability, and fault tolerance to accelerate the process and improve model performance. However, training of large-size models has exhibited numerous challenges, due to the gradient dependence that conventional approaches integrate. To improve the training efficiency of such models, gradient-free distributed methodologies have emerged fostering the gradient-independent parallel processing and efficient utilization of resources across multiple devices or nodes. However, such approaches, are usually restricted to specific applications, due to their conceptual limitations: computational and communicational requirements between partitions, limited partitioning solely into layers, limited sequential learning between the different layers, as well as training a potential model in solely synchronous mode. In this paper, we propose and evaluate, the Neuro-Distributed Cognitive Adaptive Optimization (ND-CAO) methodology, a novel gradient-free algorithm that enables the efficient distributed training of arbitrary types of neural networks, in both synchronous and asynchronous manner. Contrary to the majority of existing methodologies, ND-CAO is applicable to any possible splitting of a potential neural network, into blocks (partitions), with each of the blocks allowed to update its parameters fully asynchronously and independently of the rest of the blocks. Most importantly, no data exchange is required between the different blocks during training with the only information each block requires is the global performance of the model. Convergence of ND-CAO is mathematically established for generic neural network architectures, independently of the particular choices made, while four comprehensive experimental cases, considering different model architectures and image classification tasks, validate the algorithms\u2019 robustness and effectiveness in both synchronous and asynchronous training modes. Moreover, by conducting a thorough comparison between synchronous and asynchronous ND-CAO training, the algorithm is identified as an efficient scheme to train neural networks in a novel gradient-independent, distributed, and asynchronous manner, delivering similar \u2013 or even improved results in Loss and Accuracy measures.<\/jats:p>","DOI":"10.3233\/ica-230718","type":"journal-article","created":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T15:05:49Z","timestamp":1691939149000},"page":"19-41","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["Neuro-distributed cognitive adaptive optimization for training neural networks in a parallel and asynchronous manner"],"prefix":"10.1177","volume":"31","author":[{"given":"Panagiotis","family":"Michailidis","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"},{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (ITI-CERTH), Thessaloniki, Greece"}]},{"given":"Iakovos T.","family":"Michailidis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"},{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (ITI-CERTH), Thessaloniki, Greece"}]},{"given":"Sokratis","family":"Gkelios","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"},{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (ITI-CERTH), Thessaloniki, Greece"}]},{"given":"Georgios","family":"Karatzinis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"},{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (ITI-CERTH), Thessaloniki, Greece"}]},{"given":"Elias B.","family":"Kosmatopoulos","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"},{"name":"Information Technologies Institute, Centre for Research and Technology Hellas (ITI-CERTH), Thessaloniki, Greece"}]}],"member":"179","published-online":{"date-parts":[[2023,2,1]]},"reference":[{"key":"bibr1-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-210663"},{"key":"bibr2-ICA-230718","first-page":"1","author":"Islam S","year":"2022","journal-title":"Integrated Computer-Aided Engineering."},{"key":"bibr3-ICA-230718","first-page":"1","author":"Fern\u00e1ndez-Rodr\u00edguez JD","year":"2023","journal-title":"Integrated Computer-Aided Engineering."},{"key":"bibr4-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-2003-10108"},{"key":"bibr5-ICA-230718","volume":"25","author":"Krizhevsky A","year":"2012","journal-title":"Advances in neural information processing systems."},{"key":"bibr6-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"bibr7-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-1995-2307"},{"key":"bibr8-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-1994-1303"},{"key":"bibr9-ICA-230718","doi-asserted-by":"crossref","unstructured":"DevlinJ KamaliM SubramanianK PrasadR NatarajanP. Statistical machine translation as a language model for handwriting recognition. In: 2012 International Conference on Frontiers in Handwriting Recognition. IEEE; 2012. pp. 291-6.","DOI":"10.1109\/ICFHR.2012.273"},{"key":"bibr10-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2023.3261342"},{"key":"bibr11-ICA-230718","first-page":"1","author":"Karatzinis GD","year":"2022","journal-title":"Integrated Computer-Aided Engineering."},{"key":"bibr12-ICA-230718","doi-asserted-by":"crossref","unstructured":"SalavasidisG KapoutsisAC ChatzichristofisSA MichailidisP KosmatopoulosEB. Autonomous trajectory design system for mapping of unknown sea-floors using a team of AUVs. In: 2018 Eiuropeam Control Conference (ECC). IEEE; 2018. pp. 1080-7.","DOI":"10.23919\/ECC.2018.8550174"},{"key":"bibr13-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3390\/smartcities6010007"},{"key":"bibr14-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3390\/en16145326"},{"key":"bibr15-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-220695"},{"key":"bibr16-ICA-230718","first-page":"1","author":"Grosset J","year":"2023","journal-title":"Integrated Computer-Aided Engineering."},{"key":"bibr17-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-210660"},{"key":"bibr18-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-200637"},{"key":"bibr19-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-180584"},{"key":"bibr20-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-180587"},{"key":"bibr21-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-190613"},{"key":"bibr22-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-200620"},{"key":"bibr23-ICA-230718","first-page":"1","author":"Ruiz L","year":"2023","journal-title":"Integrated Computer-Aided Engineering."},{"key":"bibr24-ICA-230718","first-page":"1","author":"Urdiales J","year":"2023","journal-title":"Integrated Computer-Aided Engineering."},{"key":"bibr25-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-200643"},{"key":"bibr26-ICA-230718","first-page":"2","author":"Cheng B","year":"1994","journal-title":"Statistical Science."},{"key":"bibr27-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065721500301"},{"key":"bibr28-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1016\/0096-3003(94)90134-1"},{"key":"bibr29-ICA-230718","author":"Rafiei MH","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems."},{"key":"bibr30-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2018.10.065"},{"key":"bibr31-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00026-V"},{"key":"bibr32-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1111\/0885-9507.00189"},{"key":"bibr33-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-180577"},{"key":"bibr34-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-170551"},{"key":"bibr35-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-150502"},{"key":"bibr36-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-1999-6105"},{"key":"bibr37-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-2007-14301"},{"key":"bibr38-ICA-230718","doi-asserted-by":"crossref","unstructured":"AdeliH Ghosh-DastidarS. Automated EEG-based diagnosis of neurological disorders: Inventing the future of neurology. CRC press; 2010.","DOI":"10.1201\/9781439815328"},{"key":"bibr39-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2006.886855"},{"key":"bibr40-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-015-0353-9"},{"key":"bibr41-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1159\/000381950"},{"key":"bibr42-ICA-230718","unstructured":"AdeliH KumarS. Distributed computer-aided engineering. vol. 2. CRC Press; 1998."},{"key":"bibr43-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"bibr44-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"bibr45-ICA-230718","unstructured":"MostafaH RameshV CauwenberghsG. Deep supervised learning using local errors. arXiv. arXiv preprint arXiv: 171106756; 2017; 10."},{"key":"bibr46-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1145\/2742060.2743766"},{"key":"bibr47-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2654298"},{"key":"bibr48-ICA-230718","unstructured":"JouppiNP YoungC PatilN PattersonD AgrawalG BajwaR, et al. In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th annual international symposium on computer architecture; 2017. pp. 1-12."},{"key":"bibr49-ICA-230718","unstructured":"TaylorG BurmeisterR XuZ SinghB PatelA GoldsteinT. Training neural networks without gradients: A scalable admm approach. In: International conference on machine learning. PMLR 2016; pp. 2722-31."},{"key":"bibr50-ICA-230718","doi-asserted-by":"crossref","unstructured":"TeerapittayanonS McDanelB KungHT. Distributed deep neural networks over the cloud, the edge and end devices. In: 2017 IEEE 37th international conference on distributed computing systems (ICDCS). IEEE; 2017. pp. 328-39.","DOI":"10.1109\/ICDCS.2017.226"},{"key":"bibr51-ICA-230718","unstructured":"SerbA CornaA GeorgeR KhiatA RocchiF ReatoM, et al. A geographically distributed bio-hybrid neural network with memristive plasticity. arXiv preprint arXiv:170904179; 2017."},{"key":"bibr52-ICA-230718","doi-asserted-by":"crossref","unstructured":"Long WangJCS. Multilevel Data Integration with Application in Sensor Networks. 2020 American Control Conference (ACC). 2020.","DOI":"10.23919\/ACC45564.2020.9148012"},{"key":"bibr53-ICA-230718","doi-asserted-by":"crossref","unstructured":"Long WangJCS,ZhuJ. Model-Free Optimal Control using SPSA with Complex Variables. 55th Annual Conference on Information Sciences and Systems (CISS). 2021.","DOI":"10.1109\/CISS50987.2021.9400266"},{"key":"bibr54-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.912315"},{"key":"bibr55-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2020.100232"},{"key":"bibr56-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3390\/en13236228"},{"key":"bibr57-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1007\/s43926-021-00003-w"},{"key":"bibr58-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-9445(1997)123:7(880)"},{"key":"bibr59-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.448"},{"key":"bibr60-ICA-230718","unstructured":"LyuH. Convergence and complexity of block coordinate descent with diminishing radius for nonconvex optimization. arXiv preprint arXiv:201203503. 2020."},{"key":"bibr61-ICA-230718","unstructured":"ZengJ LauTTK LinS YaoY. Global convergence of block coordinate descent in deep learning. In: International conference on machine learning. PMLR; 2019; pp. 7313-23."},{"key":"bibr62-ICA-230718","unstructured":"Carreira-PerpinanM WangW. Distributed optimization of deeply nested systems. In: Artificial Intelligence and Statistics. PMLR; 2014; pp. 10-9."},{"key":"bibr63-ICA-230718","unstructured":"ZhangZ BrandM. Convergent block coordinate descent for training tikhonov regularized deep neural networks. Advances in Neural Information Processing Systems. 2017; 30."},{"key":"bibr64-ICA-230718","unstructured":"AskariA NegiarG SambharyaR GhaouiLE. Lifted neural networks. arXiv preprint arXiv:180501532; 2018."},{"key":"bibr65-ICA-230718","unstructured":"GuF AskariA El GhaouiL. Fenchel lifted networks: A lagrange relaxation of neural network training. In: International Conference on Artificial Intelligence and Statistics. PMLR; 2020; pp. 3362-71."},{"key":"bibr66-ICA-230718","unstructured":"LauTTK ZengJ WuB YaoY. A proximal block coordinate descent algorithm for deep neural network training. arXiv preprint arXiv:180309082; 2018."},{"key":"bibr67-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1137\/120887795"},{"key":"bibr68-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-017-0376-0"},{"key":"bibr69-ICA-230718","volume":"27","author":"Razaviyayn M","year":"2014","journal-title":"Advances in Neural Information Processing Systems."},{"key":"bibr70-ICA-230718","doi-asserted-by":"crossref","unstructured":"BoydS ParikhN ChuE. Distributed optimization and statistical learning via the alternating direction method of multipliers. Now Publishers Inc; 2011.","DOI":"10.1561\/9781601984616"},{"key":"bibr71-ICA-230718","unstructured":"NishiharaR LessardL RechtB PackardA JordanM. A general analysis of the convergence of ADMM. In: International Conference on Machine Learning. PMLR; 2015; pp. 343-52."},{"key":"bibr72-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-0757-z"},{"key":"bibr73-ICA-230718","doi-asserted-by":"crossref","unstructured":"ZhangZ ChenY SaligramaV. Efficient training of very deep neural networks for supervised hashing. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016; pp. 1487-95.","DOI":"10.1109\/CVPR.2016.165"},{"key":"bibr74-ICA-230718","doi-asserted-by":"crossref","unstructured":"WangJ ChaiZ ChengY ZhaoL. Toward model parallelism for deep neural network based on gradient-free ADMM framework. In: 2020 IEEE International Conference on Data Mining (ICDM). IEEE; 2020. pp. 591-600.","DOI":"10.1109\/ICDM50108.2020.00068"},{"key":"bibr75-ICA-230718","doi-asserted-by":"crossref","unstructured":"MotaJF XavierJM AguiarPM P\u00fcschelM. Distributed ADMM for model predictive control and congestion control. In: 2012 IEEE 51st IEEE Conference on Decision and Control (CDC). IEEE; 2012. pp. 5110-5.","DOI":"10.1109\/CDC.2012.6426141"},{"key":"bibr76-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2677879"},{"key":"bibr77-ICA-230718","doi-asserted-by":"crossref","unstructured":"ChangTH. A proximal dual consensus ADMM method for multi-agent constrained optimization. IEEE Transactions on Signal Processing. 2016; 64(14): 3719-34.","DOI":"10.1109\/TSP.2016.2544743"},{"key":"bibr78-ICA-230718","doi-asserted-by":"crossref","unstructured":"ChangTH HongM WangX. Multi-agent distributed optimization via inexact consensus ADMM. IEEE Transactions on Signal Processing. 2014; 63(2): 482-97.","DOI":"10.1109\/TSP.2014.2367458"},{"key":"bibr79-ICA-230718","doi-asserted-by":"crossref","unstructured":"ShiW LingQ YuanK WuG YinW. On the linear convergence of the ADMM in decentralized consensus optimization. IEEE Transactions on Signal Processing. 2014; 62(7): 1750-61.","DOI":"10.1109\/TSP.2014.2304432"},{"key":"bibr80-ICA-230718","unstructured":"XuZ TaylorG LiH FigueiredoMA YuanX GoldsteinT. Adaptive consensus ADMM for distributed optimization. In: International Conference on Machine Learning. PMLR; 2017; pp. 3841-50."},{"key":"bibr81-ICA-230718","doi-asserted-by":"crossref","unstructured":"ZhuS HongM ChenB. Quantized consensus ADMM for multi-agent distributed optimization. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2016. pp. 4134-8.","DOI":"10.1109\/ICASSP.2016.7472455"},{"key":"bibr82-ICA-230718","unstructured":"ZhangR KwokJ. Asynchronous distributed ADMM for consensus optimization. In: International conference on machine learning. PMLR; 2014; pp. 1701-9."},{"key":"bibr83-ICA-230718","doi-asserted-by":"crossref","unstructured":"WeiE OzdaglarA. Distributed alternating direction method of multipliers. In: 2012 IEEE 51st IEEE Conference on Decision and Control (CDC). IEEE; 2012. pp. 5445-50.","DOI":"10.1109\/CDC.2012.6425904"},{"key":"bibr84-ICA-230718","doi-asserted-by":"crossref","unstructured":"ChangTH HongM LiaoWC WangX. Asynchronous distributed ADMM for large-scale optimization \u2013 Part I: Algorithm and convergence analysis. IEEE Transactions on Signal Processing. 2016; 64(12): 3118-30.","DOI":"10.1109\/TSP.2016.2537271"},{"key":"bibr85-ICA-230718","doi-asserted-by":"crossref","unstructured":"KumarS JainR RajawatK. Asynchronous optimization over heterogeneous networks via consensus admm. IEEE Transactions on Signal and Information Processing over Networks. 2016; 3(1): 114-29.","DOI":"10.1109\/TSIPN.2016.2593896"},{"key":"bibr86-ICA-230718","doi-asserted-by":"publisher","DOI":"10.3390\/en14237910"},{"key":"bibr87-ICA-230718","doi-asserted-by":"crossref","unstructured":"MichailidisIT ManolisD MichailidisP DiakakiC KosmatopoulosEB. Autonomous self-regulating intersections in large-scale urban traffic networks: a Chania City case study. In: 2018 5th international conference on control, decision and information technologies (CoDIT). IEEE; 2018. pp. 853-8.","DOI":"10.1109\/CoDIT.2018.8394910"},{"key":"bibr88-ICA-230718","doi-asserted-by":"crossref","unstructured":"MichailidisIT MichailidisP AlexandridouK BrewickPT MasriSF KosmatopoulosEB, et al. Seismic Active Control under Uncertain Ground Excitation: an Efficient Cognitive Adaptive Optimization Approach. In: 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT). IEEE; 2018. pp. 847-52.","DOI":"10.1109\/CoDIT.2018.8394942"},{"key":"bibr89-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.11.046"},{"key":"bibr90-ICA-230718","doi-asserted-by":"crossref","unstructured":"MichailidisIT MichailidisP RizosA KorkasC KosmatopoulosEB. Automatically fine-tuned speed control system for fuel and travel-time efficiency: A microscopic simulation case study. In: 2017 25th Mediterranean Conference on Control and Automation (MED). IEEE; 2017. pp. 915-20.","DOI":"10.1109\/MED.2017.7984236"},{"key":"bibr91-ICA-230718","doi-asserted-by":"crossref","unstructured":"KorkasCD BaldiS MichailidisP KosmatopoulosEB. A cognitive stochastic approximation approach to optimal charging schedule in electric vehicle stations. In: 2017 25th Mediterranean Conference on Control and Automation (MED). IEEE; 2017. pp. 484-9.","DOI":"10.1109\/MED.2017.7984164"},{"key":"bibr92-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.09.014"},{"key":"bibr93-ICA-230718","unstructured":"SunT HannahR YinW. Asynchronous Coordinate Descent under More Realistic Assumptions; 2017."},{"key":"bibr94-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2682102"},{"key":"bibr95-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04146-4"},{"key":"bibr96-ICA-230718","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04359-7"}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/ICA-230718","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/ICA-230718","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/ICA-230718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:14:49Z","timestamp":1777454089000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/ICA-230718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":96,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10.3233\/ICA-230718"],"URL":"https:\/\/doi.org\/10.3233\/ica-230718","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}