Skip to content
Preprint

A Mathematical Theory of Interpretation: Rational Entropy, Spectral Readout, and Confusability as a Resource

Aug 2026 · 0 citations · 24 references
Computer Science Mathematics

Abstract

This article presents the abridged core of \emph{A Mathematical Theory of Interpretation} (MTI), which treats interpretation as observer-relative spectral measurement under an access structure. MTI makes interpretation a method-design problem: access, query, utility, and medium determine what an observer can select, identify, communicate, or refuse. On a learning-invariant Hilbert realization, Rational Entropy measures residual uncertainty across knowledge, utility, and medium. In the finite-effective regime, we classify its zero set. Pairwise confusability is equivalent to uniform atomic collapse, while a unique utility maximum can select one atom even when other zero-cost states remain non-atomic. This reverses the usual zero-error role of confusability: agreement in at least one observer direction excludes unresolved multi-atom readings, while the joint label preserves identification. The corresponding free-design capacity is the product of all but the smallest direction budget. A four-condition certificate characterizes sharp, decodable, medium-faithful, and order-independent readout on a finite commuting code sector and returns typed obstructions when those guarantees fail. Together, these results establish MTI as a theoretical basis for constructing interpretation methods with explicit access assumptions, guarantees, and failure modes.

View source

Similar papers

Preprint Aug 2026

Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

The Koopman spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition, and the spectrum is recoverable from calibration samples at rate $M^{-1/2}$ up to permutation.

Ashim Dhor, Pin-Yu Chen · 0 citations
Preprint Sep 2026

Haar-Bayesian Pure-State Prediction under Relative-Entropy Loss: Arbitrary-Effect Reduction and Global Optimality

We study Haar-Bayesian prediction of one unmeasured copy of an unknown finite-dimensional pure quantum state after an arbitrary collective measurement on $n$ observed copies. Performance is evaluated by quantum relative entropy. For a fixed measurement, the Bayes predictive state is the posterior mean and the optimized...

Masahito Hayashi, Ayanava Dasgupta, Naqueeb Ahmad Warsi · 1 citation
Open access Sep 2026

A canonical entropy-based multiscale decomposition of L1 functions

We introduce a canonical entropy-based multiscale decomposition of nonnegative L1 functions that yields both physically meaningful approximations and an injective representation. The construction produces a recursive partition of the domain-organized as a Hahn tree-in which each region carries exact mass information to...

Rajeev Rajaram, N. Ritchey · 0 citations
Preprint Aug 2026

Stabilizer Statistical Mechanics: A Framework for Efficient Quantification and Classification of Magic States

The partition function is statistical mechanics'answer to an exponentially large spectrum, distilling it into a single analytic object whose temperature dependence resolves the full structure of the underlying ensemble. We show that magic, the resource separating universal quantum computation from classically simulable...

William E. Salazar, G. Saxena, Jack S Baker et al. · 3 citations · ⚡1
#artificial intelligence Preprint Sep 2026

A Mathematical Theory of Pragmatic Information

We propose a mathematical theory of pragmatic information that connects communication, control, and decision-making. Its central notion is the isoteleia mapping, which formalizes equifinality: distinct semantic paths that lead to the same optimal action are treated as pragmatically equivalent. This mapping yields a thr...

Kai Niu, Ping Zhang · 0 citations
#machine learning Preprint Sep 2026

ALICE: In-context, Zero-shot, Mutual Information Estimation

Estimating mutual information (MI) from samples is a central objective in a variety of scientific fields. Modern neural estimators are accurate in the large-data regime, but they fall short when data is scarce, and each must be fit anew for every distribution under study. Current estimators are moreover tied to specifi...

Giulio Franzese, Simone Rossi, Pietro Michiardi · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.