Contextuality from Single-State Representations: An Information-Theoretic Principle for Adaptive Intelligence

• URL: http://arxiv.org/abs/2602.16716v1
• Date: Tue, 03 Feb 2026 19:20:10 GMT
• Title: Contextuality from Single-State Representations: An Information-Theoretic Principle for Adaptive Intelligence
• Authors: Song-Ju Kim,
• Abstract summary: We show that contextuality is not a peculiarity of quantum mechanics, but an inevitable consequence of single-state reuse in classical representations.<n>Our results identify contextuality as a general representational constraint on adaptive intelligence, independent of physical implementation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adaptive systems often operate across multiple contexts while reusing a fixed internal state space due to constraints on memory, representation, or physical resources. Such single-state reuse is ubiquitous in natural and artificial intelligence, yet its fundamental representational consequences remain poorly understood. We show that contextuality is not a peculiarity of quantum mechanics, but an inevitable consequence of single-state reuse in classical probabilistic representations. Modeling contexts as interventions acting on a shared internal state, we prove that any classical model reproducing contextual outcome statistics must incur an irreducible information-theoretic cost: dependence on context cannot be mediated solely through the internal state. We provide a minimal constructive example that explicitly realizes this cost and clarifies its operational meaning. We further explain how nonclassical probabilistic frameworks avoid this obstruction by relaxing the assumption of a single global joint probability space, without invoking quantum dynamics or Hilbert space structure. Our results identify contextuality as a general representational constraint on adaptive intelligence, independent of physical implementation.

Related papers

• Contextuality as an Information-Theoretic Obstruction to Classical Probability [0.0]
  We show that contextual statistics certify an unavoidable obstruction to classical probabilistic descriptions.<n>Specifically, any classical model that reproduces such statistics must either embed contextual dependence into the internal state or introduce additional external labels carrying nonzero information.<n>From this viewpoint, quantum probability emerges as a canonical framework that accommodates contextual operations without requiring explicit contextual encoding.
  arXiv  Detail & Related papers  (2026-01-28T02:02:55Z)
• Generalised contextuality of continuous variable quantum theory can be revealed with a single projective measurement [0.0]
  We show that a direct application of the standard definition of generalised contextuality to continuous variable systems does not envelope the statistics of some basic measurements.<n>We propose a modified definition of generalised contextuality for continuous-variable systems.
  arXiv  Detail & Related papers  (2026-01-20T15:24:26Z)
• Contextuality Derived from Minimal Decision Dynamics: Quantum Tug-of-War Decision Making [0.0]
  We show that contextuality arises generatively from physically grounded constraints on decision making.<n>Results indicate that quantum probability is not merely a descriptive convenience, but an unavoidable effective theory for adaptive decision dynamics.
  arXiv  Detail & Related papers  (2026-01-15T03:27:28Z)
• Non-Resolution Reasoning (NRR): A Computational Framework for Contextual Identity and Ambiguity Preservation [0.0]
  Current artificial intelligence systems exhibit a fundamental architectural limitation: they resolve ambiguity prematurely.<n>This premature semantic collapse stems from classical identity assumptions embedded in standard neural architectures.<n>We propose Non-Resolution Reasoning (NRR), a computational framework that treats ambiguity retention as a valid reasoning mode.
  arXiv  Detail & Related papers  (2025-12-15T16:14:32Z)
• Priors in Time: Missing Inductive Biases for Language Model Interpretability [58.07412640266836]
  We show that Sparse Autoencoders impose priors that assume independence of concepts across time, implying stationarity.<n>We introduce a new interpretability objective -- Temporal Feature Analysis -- which possesses a temporal inductive bias to decompose representations at a given time into two parts.<n>Our results underscore the need for inductive biases that match the data in designing robust interpretability tools.
  arXiv  Detail & Related papers  (2025-11-03T18:43:48Z)
• Modal Logic for Stratified Becoming: Actualization Beyond Possible Worlds [55.2480439325792]
  This article develops a novel framework for modal logic based on the idea of stratified actualization.<n>Traditional Kripke semantics treat modal operators as quantification over fully determinate alternatives.<n>We propose a system Stratified Actualization Logic (SAL) in which modalities are indexed by levels of ontological stability, interpreted as admissibility.
  arXiv  Detail & Related papers  (2025-06-12T18:35:01Z)
• Towards Understanding Extrapolation: a Causal Lens [53.15488984371969]
  We provide a theoretical understanding of when extrapolation is possible and offer principled methods to achieve it.<n>Under this formulation, we cast the extrapolation problem into a latent-variable identification problem.<n>Our theory reveals the intricate interplay between the underlying manifold's smoothness and the shift properties.
  arXiv  Detail & Related papers  (2025-01-15T21:29:29Z)
• Sequential Representation Learning via Static-Dynamic Conditional Disentanglement [58.19137637859017]
  This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between those factors by explicitly accounting for the causal relationship between the static/dynamic variables. Experiments show that the proposed approach outperforms previous complex state-of-the-art techniques in scenarios where the dynamics of a scene are influenced by its content.
  arXiv  Detail & Related papers  (2024-08-10T17:04:39Z)
• Unconventional mechanism of virtual-state population through dissipation [125.99533416395765]
  We report a phenomenon occurring in open quantum systems by which virtual states can acquire a sizable population in the long time limit. This means that the situation where the virtual state remains unpopulated can be metastable. We show how these results can be relevant for practical questions such as the generation of stable and metastable entangled states in dissipative systems of interacting qubits.
  arXiv  Detail & Related papers  (2022-02-24T17:09:43Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• Solvable Criterion for the Contextuality of any Prepare-and-Measure Scenario [0.0]
  An operationally noncontextual ontological model of the quantum statistics associated with the prepare-and-measure scenario is constructed. A mathematical criterion, called unit separability, is formulated as the relevant classicality criterion. We reformulate our results in the framework of generalized probabilistic theories.
  arXiv  Detail & Related papers  (2020-03-13T18:00:05Z)

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.