Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

• URL: http://arxiv.org/abs/2606.12471v1
• Date: Tue, 09 Jun 2026 23:00:48 GMT
• Title: Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency
• Abstract summary: We prove that statistical World Models cannot achieve near-infinite temporal consistency for any non-Gaussian system.<n>In non-Gaussian regimes, the only condition for near-infinite temporal consistency is symbolic grounding in the causal generator of the world's dynamics.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Klindt, LeCun, and Balestriero (arXiv:2605.26379) proved that Joint-Embedding Predictive Architectures (JEPAs) achieve linear identifiability, the linear recovery of the world's true latent variables, if and only if the world's latent dynamics follow a Gaussian, stationary process. This Gaussian boundary implies a fundamental limit on temporal consistency: for any non-Gaussian physical system, the representation error of a statistical World Model grows monotonically with time. We prove that this limit is an artifact of the statistical alignment mechanism, not a property of World Models in general. We introduce the Physics-Grounded Symbolic Architecture (PGSA) and prove three results: (1) a PGSA achieves exact linear identifiability for all physical regimes, regardless of the latent distribution; (2) the per-step error of a PGSA is bounded by numerical precision alone; and (3) as a direct consequence, a PGSA maintains temporal consistency for an unbounded number of transitions, a property we term near-infinite temporal consistency. We further prove that statistical World Models cannot achieve this property for any non-Gaussian system, regardless of model capacity or the volume of training data. The algebraic cores of four of the theorems are formalized in Lean 4 with Mathlib4 v4.31.0 (zero sorry placeholders); the Klindt et al. converse is taken as an external premise. The contrast establishes that symbolic grounding in the causal generator of the world's dynamics is the sufficient condition and, in non-Gaussian regimes, the only condition for near-infinite temporal consistency.

Related papers

• Computer-assisted global regularity across nonlinear families of three-dimensional periodic Navier-Stokes flows [0.0]
  I develop a computer-assisted framework that establishes global regularity for three-dimensional periodic Navier-Stokes flows.<n>The method retains the complete nonlinear residual before spectral truncation and controls the evolution until decay guarantees regularity for all subsequent times.<n>An ensemble of 4,096 configurations, supplemented by 1,600 refinement trajectories and public turbulence data, connects the mathematical observables to spectral transfer and vortex geometry.
  arXiv  Detail & Related papers  (2026-09-14T18:02:50Z)
• Nonlocal Bayesian Modeling of Continuous Spatio-Temporal Dynamics [9.926231893220061]
  We propose a principled NonLocal S-NL model (BST) for continuous-temporal fields that learns nonlocal coupling while retaining tractable inference.<n> NLBST represents the latent field via a coordinate-based spatial basis expansion and models the sequential process with a continuous-time ODE.<n>A linear-Gssianau observation model enables Kalmanssian-style sequential sparse updates under missing and irregular observations, while the spatial basis representation enables inductive prediction at unmeasured locations without retraining.
  arXiv  Detail & Related papers  (2026-06-12T09:51:07Z)
• Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis [63.07333625429548]
  We present U4D, a new framework that explicitly leverages spatial uncertainty to guide LiDAR scene generation.<n>Experiments on nuScenes and Semantic KITTI demonstrate state-of-the-art scene fidelity, temporal consistency, and downstream performance.
  arXiv  Detail & Related papers  (2026-06-01T17:24:14Z)
• When Does LeJEPA Learn a World Model? [48.74247491501631]
  A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization.<n>We prove that LeJEPA linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability.<n>We validate the theory with experiments ranging from 2D examples to 1024-dimensional latents, including distributional ablations and pixel-based robotic control.
  arXiv  Detail & Related papers  (2026-05-25T22:56:26Z)
• Conditioning Gaussian Processes on Almost Anything [19.803622987031705]
  We recast predictive sampling as an ODE with closed-form Gaussian dynamics and a likelihood-dependent guidance term that admits a simple Monte Carlo approximation.<n> Whitening isolates the irreducible non-Gaussian dynamics, minimising Wasserstein-2 transport cost and eliminating numerical stiffness.<n>These results provide a general mechanism for incorporating the full richness of real-world knowledge as conditioning information, opening a new frontier for the probabilistic modelling of real-world problems.
  arXiv  Detail & Related papers  (2026-05-20T11:23:42Z)
• On the Limits of Self-Improving in LLMs and Why AGI, ASI and the Singularity Are Not Near Without Symbolic Model Synthesis [0.01269104766024433]
  We formalise self-training in Large Language Models (LLMs) and Generative AI as a discrete-time dynamical system.<n>We derive two fundamental failure modes: (1) Entropy Decay, where finite sampling effects cause a monotonic loss of distributional diversity (mode collapse), and (2) Variance Amplification, where the loss of external grounding causes the model's representation of truth to drift as a random walk.
  arXiv  Detail & Related papers  (2026-01-05T19:50:49Z)
• U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences [54.77163447282599]
  Existing generative frameworks treat all spatial regions uniformly, overlooking the varying uncertainty across real-world scenes.<n>We present U4D, an uncertainty-aware framework for 4D LiDAR world modeling.<n>Our approach first estimates spatial uncertainty maps from a pretrained segmentation model to localize semantically challenging regions.<n>It then performs generation in a "hard-to-easy" manner through two sequential stages: (1) uncertainty-region modeling, which reconstructs high-entropy regions with fine geometric fidelity, and (2) uncertainty-conditioned completion, which synthesizes the remaining areas under learned structural priors.
  arXiv  Detail & Related papers  (2025-12-02T17:59:57Z)
• A No-Go Theorem for Shaping Quantum Resources [0.0]
  We prove a general no-go theorem for such resource shaping.<n>Every non-quadratic term necessarily couples the Gaussian and non-Gaussian sectors.<n>It defines the analytic boundary between classically simulable Gaussian dynamics and the fully universal non-Gaussian regime.
  arXiv  Detail & Related papers  (2025-10-28T16:07:48Z)
• Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises [37.02662517645979]
  We introduce FANTOM, a unified framework for causal discovery.<n>It handles non-stationary processes along with non-Gaussian and heteroscedastic noises.<n>It simultaneously infers the number of regimes and their corresponding indices and learns each regime's Directed Acyclic Graph.
  arXiv  Detail & Related papers  (2025-06-20T15:12:43Z)
• Exceptional Points and Stability in Nonlinear Models of Population Dynamics having $\mathcal{PT}$ symmetry [49.1574468325115]
  We analyze models governed by the replicator equation of evolutionary game theory and related Lotka-Volterra systems of population dynamics.<n>We study the emergence of exceptional points in two cases: (a) when the governing symmetry properties are tied to global properties of the models, and (b) when these symmetries emerge locally around stationary states.
  arXiv  Detail & Related papers  (2024-11-19T02:15:59Z)
• From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent [50.4531316289086]
  Gradient Descent (SGD) has been the method of choice for learning large-scale non-root models. An overarching paper is providing general conditions SGD converges, assuming that GF on the population loss converges. We provide a unified analysis for GD/SGD not only for classical settings like convex losses, but also for more complex problems including Retrieval Matrix sq-root.
  arXiv  Detail & Related papers  (2022-10-13T03:55:04Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Long-range level correlations in quantum systems with finite Hilbert space dimension [0.0]
  We study the spectral statistics of quantum systems with finite Hilbert spaces. We derive a theorem showing that eigenlevels in such systems cannot be globally uncorrelated.
  arXiv  Detail & Related papers  (2020-10-13T15:49:15Z)

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.