Linguistic Holonomy and Statistical Watermarks: Inner Geometry of Meaning-Preserving Transformations

• URL: http://arxiv.org/abs/2608.19369v1
• Date: Wed, 19 Aug 2026 18:36:51 GMT
• Title: Linguistic Holonomy and Statistical Watermarks: Inner Geometry of Meaning-Preserving Transformations
• Abstract summary: We show that the endpoint of transformations which move a text while leaving its content in place is the wrong statistic.<n>We adapt the formalism of linguistic loops to show that the invariant of a chain of meaning-preserving transformations factorises canonically into an endpoint part and a holonomy in the stabiliser of the initial state.<n>On the side of the detector we prove an exact identity: the residual statistic is proportional to the number of positions whose seeding window survived intact.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Statistical watermarks for language models live in the freedom of the signifier: they choose among tokens that are nearly equivalent in meaning, and they are therefore eroded by exactly those transformations which move the form of a text while leaving its content in place. The literature measures such transformations by their endpoint, through the semantic similarity between the original and the rewritten text. We show that the endpoint is the wrong statistic. Adapting the formalism of linguistic loops, we prove that the invariant of a chain of meaning-preserving transformations factorises canonically into an endpoint part and a holonomy in the stabiliser of the initial state, the second of which the semantic deficit cannot see; the loop rotation is parallel transport on the unit sphere of the embedding space, so that the analogy with the Wilson loop becomes a theorem rather than a figure of speech. On the side of the detector we prove an exact identity: the residual statistic is proportional to the number of positions whose seeding window survived intact, from which the decay law $ρ^{h+1}$ follows as the independent-edit corollary. The identity has a disconcerting consequence, which we confirm to three decimal places: at one and the same retention rate the surviving signal may be one half of the original, one quarter of it, or exactly nothing, according only to where the edits fall.

Related papers

• Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry [51.99454801210509]
  We plant a controllable latent variable inside natural-looking text.<n>A small transformer model trained on this corpus does indeed track the Bayesian posterior belief about our planted latent variable.
  arXiv  Detail & Related papers  (2026-08-27T09:45:00Z)
• Language Has Two Parameters: Narrative-Induced Semantic Plasticity and Phase-Sensitive Interpretation [0.0]
  This paper proposes that encounters alter persistent relations among simultaneously active meanings.<n>It argues that future AI agents will need persistent semantic states indexed to particular individuals and relationships.
  arXiv  Detail & Related papers  (2026-08-18T17:34:25Z)
• MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations [47.771518253102975]
  MicroVerse is a behavioral-science instrument that measures identity drift in generative agents.<n>Agents carry an immutable "soul file" (core values, moral boundaries, personality, goals) and inhabit a resource-scarce 50 x 50 environment.<n>Anti-self-deception emerges unprompted as the single largest semantic category of identity modification.
  arXiv  Detail & Related papers  (2026-08-16T16:31:42Z)
• Metaphor Tracer: A Theory-Informed Analysis of Hidden States [0.0]
  From one forward pass, without training, we score every token position on two properties.<n>The *aggregator* measures whether the position consolidates the whole text into a stable configuration.<n>The *differentiator*, whether other tokens are transiently carried into its subspace as the model reads.
  arXiv  Detail & Related papers  (2026-07-30T16:12:13Z)
• Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing [35.76482964927589]
  We test the hypothesis that concept-specific memory traces become linear objects that can be extracted once and combined arithmetically.<n>We run that test on the authors' own reference implementation, at their reported best edit strength.<n>For unlearning-as-compliance: erasure certified today does not certify the artifact after its next edit.
  arXiv  Detail & Related papers  (2026-07-06T23:45:06Z)
• Structure Before Collapse: Transient semantic geometry in next-token prediction [33.942301586178914]
  Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other.<n>This creates a puzzle: next-token prediction language models are trained predominantly with one-hot labels.<n>We find that semantic geometry emerges early in training, and that representations cluster by shared attributes.
  arXiv  Detail & Related papers  (2026-06-25T08:33:34Z)
• Embeddings for Preferences, Not Semantics [42.35314862635723]
  Modern AI is opening the door to collective decision-making in which participants express their views as free-form text.<n>Standard text embeddings measure semantic similarity, whereas distances in facility location problems and fair clustering require what we call textitpreferential similarity<n>We show that synthetic training data designed to break this correlation provably shifts the optimal scorer away from nuisance-dominated cosine and significantly improves preference prediction across 11 online deliberation datasets.
  arXiv  Detail & Related papers  (2026-05-08T18:15:14Z)
• Semantic Shift: the Fundamental Challenge in Text Embedding and Retrieval [39.73839943827917]
  Transformer-based embedding models rely on pooling to map variable-length text into a single vector.<n>We argue that the missing causal factor is emphsemantic shift: the intrinsic, structured evolution and dispersion of semantics within a text.
  arXiv  Detail & Related papers  (2026-03-22T22:58:11Z)
• Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression [102.24287051757469]
  We study self-supervised covariance estimation in deep heteroscedastic regression.<n>We derive an upper bound on the 2-Wasserstein distance between normal distributions.<n>Experiments over a wide range of synthetic and real datasets demonstrate that the proposed 2-Wasserstein bound coupled with pseudo label annotations results in a computationally cheaper yet accurate deep heteroscedastic regression.
  arXiv  Detail & Related papers  (2025-02-14T22:37:11Z)
• Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
  We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
  arXiv  Detail & Related papers  (2024-10-07T23:53:25Z)
• Distributional Semantics, Holism, and the Instability of Meaning [0.0]
  Large Language Models are built on the so-called distributional semantic approach to linguistic meaning.<n>A standard objection to holism is the charge of instability.<n>We argue that the instability that language models display is constrained by the structure and scale of relationships between words.
  arXiv  Detail & Related papers  (2024-05-20T14:53:25Z)
• The distribution of syntactic dependency distances [0.13812010983144798]
  We contribute to the characterization of the actual distribution of syntactic dependency distances.<n>We propose a new model with two exponential regimes in which the probability decay is allowed to change after a break-point.<n>We find that a two-regime model is the most likely one in all 20 languages we considered, independently of sentence length and annotation style.
  arXiv  Detail & Related papers  (2022-11-26T17:31:25Z)
• Detecting Renewal States in Chains of Variable Length via Intrinsic Bayes Factors [0.0]
  We propose the use of Intrinsic Bayes Factor to evaluate the plausibility of each set of renewal states. To show the strength of our method, we analyzed artificial datasets generated from two binary models models and one example coming from the field of Linguistics.
  arXiv  Detail & Related papers  (2021-10-14T14:57:44Z)

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.