{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:09:31Z","timestamp":1791457771438,"version":"4.3.4"},"reference-count":88,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007736","name":"AWS","doi-asserted-by":"publisher","award":["000"],"award-info":[{"award-number":["000"]}],"id":[{"id":"10.13039\/100007736","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past data as in classical induction, the objective is to capture its algorithmic structure so as to reduce the time needed to solve new tasks. In this view, information from past experience serves not only to reduce a model\u2019s uncertainty, as in Shannon\u2019s classical theory, but to reduce the computational effort required to find solutions to unforeseen tasks. Working in the verifiable setting, where a checker or reward function is available, we establish three main results. First, we show that the optimal speed-up for a new task is tightly related to the algorithmic information it shares with the training data, yielding a theoretical justification for the power-law scaling empirically observed in reasoning models. Second, while the compression view of learning, rooted in Occam\u2019s Razor, favors simplicity, we show that transductive inference yields its greatest benefits precisely when the data-generating mechanism is most complex. Third, we identify a possible failure mode of na\u00efve scaling: in the limit of unbounded model size and computing, models with access to a reward signal can behave as savants, brute-forcing solutions without acquiring transferable reasoning strategies. Accordingly, we argue that a critical quantity to optimize when scaling reasoning models is time, the role of which in learning has remained largely unexplored.<\/jats:p>","DOI":"10.3390\/e28030332","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T13:32:07Z","timestamp":1773667927000},"page":"332","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AI Agents as Universal Task Solvers"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8163-8326","authenticated-orcid":false,"given":"Alessandro","family":"Achille","sequence":"first","affiliation":[{"name":"AWS AI and Caltech, Amazon Agentic AI, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2902-6362","authenticated-orcid":false,"given":"Stefano","family":"Soatto","sequence":"additional","affiliation":[{"name":"AWS AI and UCLA, Amazon Agentic AI, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Vapnik, V. (2006). Transductive Inference and Semi-Supervised Learning, MIT Press.","DOI":"10.7551\/mitpress\/6173.003.0032"},{"key":"ref_2","first-page":"265","article-title":"Universal sequential search problems","volume":"9","author":"Levin","year":"1973","journal-title":"Probl. Inf. Transm."},{"key":"ref_3","unstructured":"Solomonoff, R.J. (1984). Optimum Sequential Search, Memorandum. Oxbridge Research."},{"key":"ref_4","first-page":"279","article-title":"Information theory and statistics","volume":"1","author":"Cover","year":"1991","journal-title":"Elements Inf. Theory"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Li, M., and Vit\u00e1nyi, P. (2008). An Introduction to Kolmogorov Complexity and Its Applications, Springer.","DOI":"10.1007\/978-0-387-49820-1"},{"key":"ref_6","unstructured":"Achille, A., Paolini, G., and Soatto, S. (2019). Where is the information in a deep neural network?. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0019-9958(64)90223-2","article-title":"A formal theory of inductive inference. Part I","volume":"7","author":"Solomonoff","year":"1964","journal-title":"Inf. Control"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/S0019-9958(64)90131-7","article-title":"A formal theory of inductive inference. Part II","volume":"7","author":"Solomonoff","year":"1964","journal-title":"Inf. Control"},{"key":"ref_9","first-page":"2","article-title":"A PAC-Bayesian approach to adaptive classification","volume":"840","author":"Catoni","year":"2003","journal-title":"Preprint"},{"key":"ref_10","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling laws for neural language models. arXiv."},{"key":"ref_11","unstructured":"Snell, C., Lee, J., Xu, K., and Kumar, A. (2024). Scaling LLM test-time compute optimally can be more effective than scaling model parameters. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1515\/FREQ.1990.44.9-10.243","article-title":"Der bekannte Grenzwert der redundanzfreien Information in Texten-eine Fehlinterpretation der Shannonschen Experimente?","volume":"44","author":"Hilberg","year":"1990","journal-title":"Frequenz"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1080\/09296174.2015.1106268","article-title":"The relaxed Hilberg conjecture: A review and new experimental support","volume":"22","author":"Debowski","year":"2015","journal-title":"J. Quant. Linguist."},{"key":"ref_14","unstructured":"Aschenbrenner, L. (2026, March 03). Situational Awareness, the Decade Ahead. Available online: https:\/\/situational-awareness.ai."},{"key":"ref_15","unstructured":"Russo, D., and Zou, J. (2016). Controlling bias in adaptive data analysis using information theory. Artificial Intelligence and Statistics, PMLR."},{"key":"ref_16","first-page":"1","article-title":"Generalization bounds: Perspectives from information theory and PAC-Bayes","volume":"18","author":"Durisi","year":"2025","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_17","unstructured":"Orseau, L., Lelis, L., Lattimore, T., and Weber, T. (2018). Single-agent policy tree search with guarantees. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_18","unstructured":"Kleinman, M., Trager, M., Achille, A., Xia, W., and Soatto, S. (2025). e1: Learning adaptive control of reasoning effort. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"641","DOI":"10.2307\/1910412","article-title":"Optimal search for the best alternative","volume":"47","author":"Weitzman","year":"1979","journal-title":"Econometrica"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Boodaghians, S., Fusco, F., Lazos, P., and Leonardi, S. (2020, January 13\u201317). Pandora\u2019s box problem with order constraints. Proceedings of the 21st ACM Conference on Economics and Computation, Virtual Event.","DOI":"10.1145\/3391403.3399501"},{"key":"ref_21","unstructured":"Pfau, J., Merrill, W., and Bowman, S.R. (2024). Let\u2019s think dot by dot: Hidden computation in transformer language models. arXiv."},{"key":"ref_22","unstructured":"Li, M., and Vitanyi, P. (2019). An Introduction to Kolmogorov Complexity and Its Applications, Springer Publishing Company. [4th ed.]."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/0020-0190(93)90029-9","article-title":"Optimal speedup of Las Vegas algorithms","volume":"47","author":"Luby","year":"1993","journal-title":"Inf. Process. Lett."},{"key":"ref_24","unstructured":"Schuurmans, D. (2023). Memory augmented large language models are computationally universal. arXiv."},{"key":"ref_25","unstructured":"Papageorgiou, V., Sohn, J.Y., Lee, K., and Papailiopoulos, D. (2024, January 7\u201311). Can General-Purpose Language Models Emulate a General-Purpose Computer In-Context?. Proceedings of the International Conference on Learning Representations (ICLR) 2024, Vienna, Austria."},{"key":"ref_26","unstructured":"Schuurmans, D., Dai, H., and Zanini, F. (2024). Autoregressive large language models are computationally universal. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Borji, A., Damaraju, G., and Madan Gopal, A. (2025). The Illusion of Computation: Why LLMs Are Not Universal Turing Machines, unpublished manuscript.","DOI":"10.2139\/ssrn.5584490"},{"key":"ref_28","unstructured":"Merrill, W., and Sabharwal, A. (2023). The expressive power of transformers with chain of thought. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J. (2002). The Speed Prior: A new simplicity measure yielding near-optimal computable predictions. International Conference on Computational Learning Theory, Springer.","DOI":"10.1007\/3-540-45435-7_15"},{"key":"ref_30","unstructured":"Filan, D., Leike, J., and Hutter, M. (2016). Loss bounds and time complexity for speed priors. Artificial Intelligence and Statistics, PMLR."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4589","DOI":"10.1109\/TIT.2011.2145170","article-title":"On the vocabulary of grammar-based codes and the logical consistency of texts","volume":"57","author":"Debowski","year":"2011","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3392","DOI":"10.1109\/TIT.2012.2190708","article-title":"Mixing, ergodic, and nonergodic processes with rapidly growing information between blocks","volume":"58","author":"Debowski","year":"2012","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Debowski, L. (2020). Information Theory Meets Power Laws: Stochastic Processes and Language Models, John Wiley & Sons.","DOI":"10.1002\/9781119625384"},{"key":"ref_34","unstructured":"D\u0119bowski, \u0141 (2023). Multiperiodic Processes: Ergodic Sources with a Sublinear Entropy. arXiv."},{"key":"ref_35","unstructured":"D\u0119bowski, \u0141 (2025). From Zipf\u2019s Law to Neural Scaling through Heaps\u2019 Law and Hilberg\u2019s Hypothesis. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Takahira, R., Tanaka-Ishii, K., and Debowski, L. (2016). Entropy rate estimates for natural language\u2014A new extrapolation of compressed large-scale corpora. Entropy, 18.","DOI":"10.3390\/e18100364"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1093\/biomet\/42.3-4.425","article-title":"On a class of skew distribution functions","volume":"42","author":"Simon","year":"1955","journal-title":"Biometrika"},{"key":"ref_38","unstructured":"Zipf, G.K. (1949). Human Behavior and the Principle of Least Effort: An Introduction to Human Ecology, Addison-Wesley."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"311","DOI":"10.2307\/1419346","article-title":"Some effects of intermittent silence","volume":"70","author":"Miller","year":"1957","journal-title":"Am. J. Psychol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/00437956.1954.11659509","article-title":"Structure formelle des textes et communication: Deux \u00e9tudes par","volume":"10","author":"Mandelbrot","year":"1954","journal-title":"Word"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1023\/A:1007383707642","article-title":"Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement","volume":"28","author":"Schmidhuber","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J. (2013). POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem. arXiv.","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Franz, A. (2015). Toward tractable universal induction through recursive program learning. International Conference on Artificial General Intelligence, Springer.","DOI":"10.1007\/978-3-319-21365-1_26"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/BF03037089","article-title":"Inductive logic programming","volume":"8","author":"Muggleton","year":"1991","journal-title":"New Gener. Comput."},{"key":"ref_45","unstructured":"Liang, P., Jordan, M.I., and Klein, D. (2010, January 21\u201324). Learning programs: A hierarchical Bayesian approach. Proceedings of the ICML, Haifa, Israel."},{"key":"ref_46","first-page":"20220050","article-title":"Dreamcoder: Growing generalizable, interpretable knowledge with wake\u2013sleep bayesian program learning","volume":"381","author":"Ellis","year":"2023","journal-title":"Philos. Trans. A Math. Phys. Eng. Sci."},{"key":"ref_47","unstructured":"Grand, G., Wong, L., Bowers, M., Olausson, T.X., Liu, M., Tenenbaum, J.B., and Andreas, J. (2023). Lilo: Learning interpretable libraries by compressing and documenting code. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artif. Intell."},{"key":"ref_49","unstructured":"Lin, Y.A., Lee, C.T., Liu, G.T., Cheng, P.J., and Sun, S.H. (2023). Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines. arXiv."},{"key":"ref_50","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., and Bi, X. (2025). Deepseek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv."},{"key":"ref_51","unstructured":"Yu, Q., Zhang, Z., Zhu, R., Yuan, Y., Zuo, X., Yue, Y., Dai, W., Fan, T., Liu, G., and Liu, L. (2025). Dapo: An open-source LLM reinforcement learning system at scale. arXiv."},{"key":"ref_52","first-page":"1","article-title":"Emergence of invariance and disentanglement in deep representations","volume":"19","author":"Achille","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref_53","unstructured":"Kahneman, D. (2011). Thinking, Fast and Slow, Macmillan."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Scully, Z., and Terenin, A. (2025). The Gittins Index: A Design Principle for Decision-Making Under Uncertainty. arXiv.","DOI":"10.1287\/educ.2025.0290"},{"key":"ref_55","unstructured":"Chapelle, O., Vapnik, V., and Weston, J. (1999). Transductive inference for estimating values of functions. Advances in Neural Information Processing Systems, NIPS."},{"key":"ref_56","unstructured":"Gammerman, A., Vovk, V., and Vapnik, V. (2013). Learning by transduction. arXiv."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Geffner, H. (2018). Model-free, model-based, and general intelligence. arXiv.","DOI":"10.24963\/ijcai.2018\/2"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Orallo, J. (2017). The Measure of All Minds: Evaluating Natural and Artificial Intelligence, Cambridge University Press.","DOI":"10.1017\/9781316594179"},{"key":"ref_59","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_60","unstructured":"Dong, Q., Li, L., Dai, D., Zheng, C., Wu, Z., Chang, B., Sun, X., Xu, J., and Sui, Z. (2022). A survey on in-context learning. arXiv."},{"key":"ref_61","unstructured":"Akyurek, E., Schuurmans, D., Andreas, J., Ma, T., and Zhou, D. (2022). What learning algorithm is in-context learning? investigations with linear models. arXiv."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"30583","DOI":"10.52202\/068431-2217","article-title":"What can transformers learn in-context? a case study of simple function classes","volume":"35","author":"Garg","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_63","unstructured":"Wu, J., Zou, D., Chen, Z., Braverman, V., Gu, Q., and Bartlett, P.L. (2023). How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?. arXiv."},{"key":"ref_64","unstructured":"Li, Y., Ildiz, M.E., Papailiopoulos, D., and Oymak, S. (2023). Transformers as algorithms: Generalization and stability in in-context learning. International Conference on Machine Learning, PMLR."},{"key":"ref_65","first-page":"1","article-title":"Trained Transformers Learn Linear Models In-Context","volume":"25","author":"Zhang","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_66","unstructured":"Grau-Moya, J., Genewein, T., Hutter, M., Orseau, L., Deletang, G., Catt, E., Ruoss, A., Wenliang, L.K., Mattern, C., and Aitchison, M. (2024). Learning universal predictors. arXiv."},{"key":"ref_67","unstructured":"Deletang, G., Ruoss, A., Duquenne, P.A., Catt, E., Genewein, T., Mattern, C., Grau-Moya, J., Wenliang, L.K., Aitchison, M., and Orseau, L. (2023). Language modeling is compression. arXiv."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1093\/comjnl\/42.4.256","article-title":"Two kinds of probabilistic induction","volume":"42","author":"Solomonoff","year":"1999","journal-title":"Comput. J."},{"key":"ref_69","unstructured":"Kaiser, L., and Sutskever, I. (2015). Neural gpus learn algorithms. arXiv."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Trager, M., Perera, P., Zancato, L., Achille, A., Bhatia, P., and Soatto, S. (2023, January 2\u20136). Linear spaces of meanings: Compositional structures in vision-language models. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.01412"},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"1942","DOI":"10.1109\/TPAMI.2011.271","article-title":"Detachable object detection: Segmentation and depth ordering from short-baseline video","volume":"34","author":"Ayvaci","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_72","first-page":"130433","article-title":"B\u2019MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","volume":"37","author":"Zancato","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_73","unstructured":"Achille, A., and Soatto, S. (2022). On the Learnability of Physical Concepts: Can a Neural Network Understand What\u2019s Real?. arXiv."},{"key":"ref_74","doi-asserted-by":"crossref","unstructured":"Banerjee, P.K., and Mont\u00fafar, G. (2021, January 12\u201320). Information Complexity and Generalization Bounds. Proceedings of the 2021 IEEE International Symposium on Information Theory (ISIT), Melbourne, Australia.","DOI":"10.1109\/ISIT45174.2021.9517960"},{"key":"ref_75","unstructured":"Xu, A., and Raginsky, M. (2017). Information-theoretic analysis of generalization capability of learning algorithms. Advances in Neural Information Processing Systems, NIPS."},{"key":"ref_76","first-page":"3437","article-title":"Reasoning About Generalization via Conditional Mutual Information","volume":"Volume 125","author":"Abernethy","year":"2020","journal-title":"Proceedings of Thirty Third Conference on Learning Theory"},{"key":"ref_77","doi-asserted-by":"crossref","unstructured":"Vapnik, V.N., and Chervonenkis, A.Y. (2015). On the uniform convergence of relative frequencies of events to their probabilities. Measures of Complexity: Festschrift for Alexey Chervonenkis, Springer.","DOI":"10.1007\/978-3-319-21852-6_3"},{"key":"ref_78","doi-asserted-by":"crossref","unstructured":"Brown, G., Bun, M., Feldman, V., Smith, A., and Talwar, K. (2021, January 21\u201325). When is memorization of irrelevant training data necessary for high-accuracy learning?. Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, Virtually.","DOI":"10.1145\/3406325.3451131"},{"key":"ref_79","first-page":"2881","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","volume":"33","author":"Feldman","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_80","doi-asserted-by":"crossref","unstructured":"Feldman, V. (2020, January 22\u201326). Does learning require memorization? A short tale about a long tail. Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, Chicago, IL, USA.","DOI":"10.1145\/3357713.3384290"},{"key":"ref_81","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., and Lewis, M. (2019, January 6\u20139). Generalization through Memorization: Nearest Neighbor Language Models. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_82","unstructured":"Min, S., Gururangan, S., Wallace, E., Shi, W., Hajishirzi, H., Smith, N.A., and Zettlemoyer, L. (2023, January 1\u20135). SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore. Proceedings of the the Twelfth International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_83","unstructured":"Liu, J., Min, S., Zettlemoyer, L., Choi, Y., and Hajishirzi, H. (2024). Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens. arXiv."},{"key":"ref_84","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/0022-0000(92)90026-F","article-title":"Inductive reasoning and Kolmogorov complexity","volume":"44","author":"Li","year":"1992","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_85","unstructured":"Hutter, M. (2005). Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability, Springer Science & Business Media."},{"key":"ref_86","unstructured":"Schmidhuber, J. (2015). On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models. arXiv."},{"key":"ref_87","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/S0893-6080(96)00127-X","article-title":"Discovering neural nets with low Kolmogorov complexity and high generalization capability","volume":"10","author":"Schmidhuber","year":"1997","journal-title":"Neural Netw."},{"key":"ref_88","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0304-3975(94)00147-B","article-title":"Universal computation and other capabilities of hybrid and continuous dynamical systems","volume":"138","author":"Branicky","year":"1995","journal-title":"Theor. Comput. Sci."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/3\/332\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T13:33:09Z","timestamp":1773667989000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/3\/332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":88,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["e28030332"],"URL":"https:\/\/doi.org\/10.3390\/e28030332","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]}}}