We formulate a statistical physics framework to model a networked stochastic dynamical system exhibiting bistability, driven by additive noise and social conformity. We apply this model to understand and mitigate AI-induced delusional spiraling-a phenomenon where algorithmic sycophancy from Large Language Models continuously reinforces inaccurate beliefs within a socially interacting society.
arXiv:2511. 02258v3 Announce Type: replace-cross Abstract: This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD).
By Parsa Rangriz
arXiv:2511.12836v2 Announce Type: replace-cross
Abstract: Sampling from a target distribution induced by training data is central to Bayesian learning, with Stochastic Gradient Langevin Dynamics (SGL...
By Waheed U. Bajwa, Mert Gurbuzbalaban, Mustafa Ali Kutbay, Lingjiong Zhu, Muhammad Zulqarnain
arXiv:2605. 30432v2 Announce Type: replace-cross Abstract: Social systems consist of networks of individuals who influence one another through social interactions.
By Moyi Tian, Daniel A. Messenger, Vanja Dukic, Nancy Rodr\'iguez, David M. Bortz
arXiv:2606. 03067v1 Announce Type: cross Abstract: A recurring data mining task in complex networks is to determine how individual nodes contribute to system behavior.
By Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge
The paper introduces a supervised, scale‑shared neural architecture for two‑dimensional site percolation, implementing a neural renormalization group flow. The model recursively applies a learned coarse‑graining rule across scales, producing a latent field that predicts crossing probability and a fine‑graining decoder that reconstructs the largest‑cluster mask. Trained only on small lattices, it extrapolates to larger systems, accurately recovers the spanning cluster, and yields observables that follow expected finite‑size scaling near the critical point, highlighting the importance of critical fluctuations in the latent representation.