Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry

• URL: http://arxiv.org/abs/2605.16325v1
• Date: Tue, 05 May 2026 05:33:57 GMT
• Title: Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
• Abstract summary: Non-equilibrium statistical physics has identified phase transitions in driven chemical reaction networks underlying prebiotic selection.<n>We propose a perspective in which both classes of phenomena admit a common description as driven informational systems.<n>We outline the geometric structure of this framework, identify falsifiable predictions distinguishing it from single-field alternatives, and show consistency with recent empirical findings.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Phase-transition phenomena in deep learning (grokking, emergent capabilities, and ontological reorganization under context shift) have been studied through several lenses, including representational compression, singular learning theory, and information-theoretic progress measures. Independently, non-equilibrium statistical physics has identified phase transitions in driven chemical reaction networks underlying prebiotic selection, with empirical signatures that are difficult to reproduce within single-field gradient accounts. We propose a perspective in which both classes of phenomena admit a common description as driven informational systems: stochastic processes governed by two gradient fields, an entropy production rate Sigma and an information quasi-potential Phi_I := -ln p*, where p* is the stationary density. Within this framework we introduce two candidate order parameters: an adversarial breakdown threshold alpha_dagger and a self-referential coupling threshold kappa_c. The joint scaling of (alpha_dagger, kappa_c) defines a candidate universality class with exponents (gamma_1, gamma_2). We outline the geometric structure of this framework, identify falsifiable predictions distinguishing it from single-field alternatives, and show consistency with recent empirical findings (2024--2026) on alignment transitions, adversarial breakdown scaling, and partial introspection in large language models.

Related papers

• Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization [17.107790125434516]
  We argue that the physical sciences offer a principled and underexplored vocabulary for reasoning about dynamics.<n>We instantiate this position through the lens of material Crystallization, which is a well-studied thermodynamic phase transition.<n>We propose intuitive metrics to verify the transitions between these phases, and validate the idea across a range of random tasks.
  arXiv  Detail & Related papers  (2026-06-29T08:09:55Z)
• Emergence via Phase Transitions: Mechanism Landscapes and Universal Convergence Across Complex Systems [0.0]
  Across machine learning, biology, and physics, independently evolving systems often converge toward strikingly similar high-level structures.<n>We propose the Hierarchical Emergence Framework (HEF) as a candidate universality framework for such convergence phenomena.<n>HEF is not presented as a universal theory of emergence, but as a falsifiable mathematical scaffold for studying convergence phenomena across complex systems.
  arXiv  Detail & Related papers  (2026-05-25T18:32:52Z)
• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking [49.1352577985191]
  We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task.<n>Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training dynamics.
  arXiv  Detail & Related papers  (2026-02-18T20:25:13Z)
• Mechanisms of AI Protein Folding in ESMFold [60.598995350547]
  We trace how ESMFold folds a beta hairpin, a prevalent structural motif.<n>We demonstrate that the mechanisms underlying structural decisions of ESMFold can be localized, traced through interpretable representations, and manipulated with strong causal effects.
  arXiv  Detail & Related papers  (2026-02-05T18:54:54Z)
• Causal Representation Meets Stochastic Modeling under Generic Geometry [49.24293444627916]
  We develop causal representation learning for continuous-time latent point processes.<n>We develop MUTATE, an identifiable variational autoencoder framework with a time-adaptive transition module.<n>Across simulated and empirical studies, we find that MUTATE can effectively answer scientific questions.
  arXiv  Detail & Related papers  (2026-02-04T20:40:53Z)
• Understanding Catastrophic Interference: On the Identifibility of Latent Representations [67.05452287233122]
  Catastrophic interference, also known as catastrophic forgetting, is a fundamental challenge in machine learning.<n>We propose a novel theoretical framework that formulates catastrophic interference as an identification problem.<n>Our approach provides both theoretical guarantees and practical performance improvements across both synthetic and benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-27T00:53:32Z)
• Class-wise Activation Unravelling the Engima of Deep Double Descent [0.0]
  Double descent presents a counter-intuitive aspect within the machine learning domain. In this study, we revisited the phenomenon of double descent and discussed the conditions of its occurrence.
  arXiv  Detail & Related papers  (2024-05-13T12:07:48Z)
• Localization, fractality, and ergodicity in a monitored qubit [0.5892638927736115]
  We study the statistical properties of a single two-level system (qubit) subject to repetitive ancilla-based measurements. This setup is a fundamental minimal model for exploring the interplay between the unitary dynamics of the system and the nonunitaryity introduced by quantum measurements.
  arXiv  Detail & Related papers  (2023-10-03T12:10:30Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Asymptotic phase-locking and synchronization in two-qubit systems [0.0]
  The paper concerns spontaneous phase-locking and synchronization in two-qubit continuous Markovian evolution described by Lindbladian dynamics with normal Lindblad operators. The possibility of entanglement production playing the role of a phase-locking witness is rebutted by three analytically treatable examples.
  arXiv  Detail & Related papers  (2022-10-13T19:45:26Z)
• Gaussian Process States: A data-driven representation of quantum many-body physics [59.7232780552418]
  We present a novel, non-parametric form for compactly representing entangled many-body quantum states. The state is found to be highly compact, systematically improvable and efficient to sample. It is also proven to be a universal approximator' for quantum states, able to capture any entangled many-body state with increasing data set size.
  arXiv  Detail & Related papers  (2020-02-27T15:54:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.