Symmetry-Constrained Language-Guided Program Synthesis for Discovering Governing Equations from Noisy and Partial Observations

• URL: http://arxiv.org/abs/2603.06869v1
• Date: Fri, 06 Mar 2026 20:42:36 GMT
• Title: Symmetry-Constrained Language-Guided Program Synthesis for Discovering Governing Equations from Noisy and Partial Observations
• Abstract summary: We introduce SymLang (Symmetry-constrained Language-guided equation discovery), a unified framework that brings together three previously separate ideas.<n>Across 133 dynamical systems SymLang achieves an exact structural recovery rate of 83.7% under 10% observational noise.<n>In all tested regimes the framework correctly identifies structural degeneracy, reporting it explicitly rather than returning a confidently wrong single equation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discovering compact governing equations from experimental observations is one of the defining objectives of quantitative science, yet practical discovery pipelines routinely fail when measurements are noisy, relevant state variables are unobserved, or multiple symbolic structures explain the data equally well within statistical uncertainty. Here we introduce SymLang (Symmetry-constrained Language-guided equation discovery), a unified framework that brings together three previously separate ideas: (i) typed symmetry-constrained grammars that encode dimensional analysis, group-theoretic invariance, and parity constraints as hard production rules, eliminating on average 71.3% of candidate expression trees before any fitting; (ii) language-model-guided program synthesis in which a fine-tuned 7B-parameter proposer, conditioned on interpretable data descriptors, efficiently navigates the constrained search space; and (iii) MDL-regularized Bayesian model selection coupled with block-bootstrap stability analysis that quantifies structural uncertainty rather than committing to a single best equation. Across 133 dynamical systems spanning classical mechanics, electrodynamics, thermodynamics, population dynamics, and nonlinear oscillators, SymLang achieves an exact structural recovery rate of 83.7% under 10% observational noise - a 22.4 percentage-point improvement over the next-best baseline - while reducing out-of-distribution extrapolation error by 61% and near-eliminating conservation-law violations (3.1 x 10-3 vs. 187.3 x 10-3 physical drift for the closest competitor). In all tested regimes the framework correctly identifies structural degeneracy, reporting it explicitly rather than returning a confidently wrong single equation. The framework is fully open-source and reproducible, providing a principled pathway from raw data to interpretable, physically auditable symbolic laws.

Related papers

• Synthetic Nearest Neighbors: Extending Synthetic Controls for Matrix Completion with Missing Not at Random Data [15.592755905264388]
  We develop a causal framework for matrix completion under missing not at random (MNAR) data.<n>Our approach relaxes two assumptions common in MNAR matrix completion: positivity and independence of observation indicators.<n> Simulation studies corroborate the theoretical findings across a range of missingness designs and observation patterns.
  arXiv  Detail & Related papers  (2026-09-11T22:50:25Z)
• Evaluating a 4B open-weights local LLM for agentic DFT workflows: a literature reproducibility audit [0.0]
  This work evaluates an openweights Qwen3:4B model executing an autonomous scientific pipeline across varying hardware constraints.<n>The system extracts parameters from unstructured text, translates them into density functional theory (DFT) inputs, and drives simulations to convergence.
  arXiv  Detail & Related papers  (2026-08-30T08:59:05Z)
• Weak Dominant Balance for Robust Identification of Dynamically Consistent Fluid Flow Structure [4.791713151156053]
  We present weak dominant balance, a derivative-free framework that projects governing equations into a weak (integral) formulation.<n>The method sustains accurate regime identification under severe noise where existing approaches categorically fail.<n>It delivers the first data-driven decomposition of a third-order partial differential equation applied to turbulent duct flow.
  arXiv  Detail & Related papers  (2026-06-27T19:05:50Z)
• CasualSynth: Generating Structurally Sound Synthetic Data [44.80087038178069]
  Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the target domain.<n>We introduce Causal Synth, a framework that decouples causal structure generation from semantic realization, yielding synthetic data that is both causally valid and linguistically rich.
  arXiv  Detail & Related papers  (2026-05-17T16:21:01Z)
• Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection [13.891522069967507]
  We present an information-geometric framework providing the first rigorous characterization of MoE dynamics specialization.<n>Our key insight is that expert routing distributions evolve on the probability simplex equipped with the Fisher information metric.
  arXiv  Detail & Related papers  (2026-04-16T00:28:41Z)
• CircuitSynth: Reliable Synthetic Data Generation [44.80087038178069]
  Large Language Models (LLMs) frequently suffer from hallucinations, logical inconsistencies, and mode collapse when tasked with structured generation.<n>Existing approaches, such as prompting or retrieval-augmented generation, lack the mechanisms to balance linguistic expressivity with formal guarantees regarding validity and coverage.<n>We propose Circuit Synth, a novel neuro-symbolic framework that decouples semantic reasoning from surface realization.
  arXiv  Detail & Related papers  (2026-04-11T09:18:52Z)
• Asymptotic Semantic Collapse in Hierarchical Optimization [0.5729426778193398]
  Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics.<n>We study this effect under the name Asymptotic Semantic Collapse in Hierarchical Optimization.<n>We show that repeated interactions with Peripheral Agent Nodes drive an alignment that minimizes a global loss.
  arXiv  Detail & Related papers  (2026-02-01T00:02:01Z)
• Knowledge-Informed Kernel State Reconstruction for Interpretable Dynamical System Discovery [46.9843470803458]
  MAAT (Model Aware Approximation of Trajectories) is a framework for symbolic discovery built on knowledge-informed Kernel State Reconstruction.<n>It substantially reduces state-estimation MSE for trajectories and derivatives used by downstream symbolic regression.
  arXiv  Detail & Related papers  (2026-01-29T21:15:52Z)
• Covariate-assisted Grade of Membership Models via Shared Latent Geometry [0.7939348535496568]
  The grade of membership model is a flexible latent variable model for analyzing multivariate categorical data through individual-level mixed membership scores.<n>Traditional approaches to incorporating auxiliary covariates typically rely on fully specified joint likelihoods, which are computationally intensive and sensitive to misspecification.<n>We introduce a covariate-assisted grade of membership model that integrates response and covariate information by exploiting their shared low-rank simplex geometry.
  arXiv  Detail & Related papers  (2026-01-24T02:30:36Z)
• Wasserstein Regression as a Variational Approximation of Probabilistic Trajectories through the Bernstein Basis [41.99844472131922]
  Existing approaches often ignore the geometry of the probability space or are computationally expensive.<n>A new method is proposed that combines the parameterization of probability trajectories using a Bernstein basis and the minimization of the Wasserstein distance between distributions.<n>The developed approach combines geometric accuracy, computational practicality, and interpretability.
  arXiv  Detail & Related papers  (2025-10-30T15:36:39Z)
• A Bayesian Framework for Symmetry Inference in Chaotic Attractors [0.0]
  We present a framework that formulates symmetry detection as probabilistic model selection over a lattice of candidate subgroups.<n>An application to human gait dynamics reveals symmetry changes induced by mechanical constraints.
  arXiv  Detail & Related papers  (2025-10-18T13:49:35Z)
• Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps [41.371172458797524]
  Non-identifiability of gating parameters up to common translations, intrinsic gate-expert interactions, and tight numerator-denominator coupling are addressed.<n>For model selection, we adapt dendrogram-guided SGMoE, yielding a consistent, sweep-free selector of the number of experts that attains optimal parameter rates.<n>On a dataset of drought-identifiable maize traits, our dendrogram-guided SGMoE selects two experts, exposes a clear mixing hierarchy, stabilizes the likelihood early, and yields interpretable genotype-phenotype maps.
  arXiv  Detail & Related papers  (2025-10-14T17:23:44Z)
• Discovering Governing Equations in the Presence of Uncertainty [11.752763800308276]
  In this work, we theorize that accounting for system variability together with measurement noise is the key to consistently discover the governing equations underlying dynamical systems.<n>We show that SIP consistently identifies the correct equations by an average of 82% relative to the Sparse Identification Dynamics (SINDy) approach and its variant.
  arXiv  Detail & Related papers  (2025-07-13T18:31:25Z)
• A Priori Denoising Strategies for Sparse Identification of Nonlinear Dynamical Systems: A Comparative Study [68.8204255655161]
  We investigate and compare the performance of several local and global smoothing techniques to a priori denoise the state measurements. We show that, in general, global methods, which use the entire measurement data set, outperform local methods, which employ a neighboring data subset around a local point.
  arXiv  Detail & Related papers  (2022-01-29T23:31:25Z)
• Neuro-Symbolic Entropy Regularization [78.16196949641079]
  In structured prediction, the goal is to jointly predict many output variables that together encode a structured object. One approach -- entropy regularization -- posits that decision boundaries should lie in low-probability regions. We propose a loss, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object.
  arXiv  Detail & Related papers  (2022-01-25T06:23:10Z)
• Unifying supervised learning and VAEs -- coverage, systematics and goodness-of-fit in normalizing-flow based neural network models for astro-particle reconstructions [0.0]
  Statistical uncertainties, coverage, systematic uncertainties or a goodness-of-fit measure are often not calculated. We show that a KL-divergence objective of the joint distribution of data and labels allows to unify supervised learning and variational autoencoders. We discuss how to calculate coverage probabilities without numerical integration for specific "base-ordered" contours.
  arXiv  Detail & Related papers  (2020-08-13T11:28:57Z)
• Sparse Identification of Nonlinear Dynamical Systems via Reweighted $\ell_1$-regularized Least Squares [62.997667081978825]
  This work proposes an iterative sparse-regularized regression method to recover governing equations of nonlinear systems from noisy state measurements. The aim of this work is to improve the accuracy and robustness of the method in the presence of state measurement noise.
  arXiv  Detail & Related papers  (2020-05-27T08:30:15Z)

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.