arXiv subjects

Dustin Bryant

Publications and source records attributed to Dustin Bryant.

3 recordsLinked to original sources

arXiv2026

Munkres' General Topology Autoformalized in Isabelle/HOL

We describe an experiment in LLM-assisted autoformalization that produced over 85,000 lines of Isabelle/HOL code covering all 39 sections of Munkres' Topology (general topology, Chapters 2--8), from topological spaces through dimension theory. The LLM-based coding agents (initially ChatGPT 5.2 and then Claude Opus 4.6) used 24 active days for that. The formalization is complete: all 806 formal results are fully proved with zero sorry's. Proved results include the Tychonoff theorem, the Baire category theorem, the Nagata--Smirnov and Smirnov metrization theorems, the Stone--\v{C}ech compactification, Ascoli's theorem, the space-filling curve, and others. The methodology is based on a "sorry-first" declarative proof workflow combined with bulk use of sledgehammer - two of Isabelle major strengths. This leads to relatively fast autoformalization progress. We analyze the resulting formalization in detail, analyze the human--LLM interaction patterns from the session log, and briefly compare with related autoformalization efforts in Megalodon, HOL Light, and Naproche. The results indicate that LLM-assisted formalization of standard mathematical textbooks in Isabelle/HOL is quite feasible, cheap and fast, even if some human supervision is useful.

cs.AI↗

arXiv2025

Formal Analysis of the Sigmoid Function and Formal Proof of the Universal Approximation Theorem

This paper presents a formalized analysis of the sigmoid function and a fully mechanized proof of the Universal Approximation Theorem (UAT) in Isabelle/HOL, a higher-order logic theorem prover. The sigmoid function plays a fundamental role in neural networks; yet, its formal properties, such as differentiability, higher-order derivatives, and limit behavior, have not previously been comprehensively mechanized in a proof assistant. We present a rigorous formalization of the sigmoid function, proving its monotonicity, smoothness, and higher-order derivatives. We provide a constructive proof of the UAT, demonstrating that neural networks with sigmoidal activation functions can approximate any continuous function on a compact interval. Our work identifies and addresses gaps in Isabelle/HOL's formal proof libraries and introduces simpler methods for reasoning about the limits of real functions. By exploiting theorem proving for AI verification, our work enhances trust in neural networks and contributes to the broader goal of verified and trustworthy machine learning.

cs.LO↗

arXiv2025

Verifying Numerical Methods with Isabelle/HOL

Modern machine learning pipelines are built on numerical algorithms. Reliable numerical methods are thus a prerequisite for trustworthy machine learning and cyber-physical systems. Therefore, we contribute a framework for verified numerical methods in Isabelle/HOL based on ITrees. Our user-friendly specification language enables the direct declaration of numerical programs that can be annotated with variants and invariants for reasoning about correctness specifications. The generated verification conditions can be discharged via automated proof methods and lemmas from the HOL-Analysis library. The ITrees foundation interacts with Isabelle's code generator to export source code. This provides an end-to-end path from formal specifications with machine-checked guarantees to executable sources. We illustrate the process of modelling numerical methods and demonstrate the effectiveness of the verification by focusing on two well-known methods, the bisection method and the fixed-point iteration method. We also contribute crucial extensions to the libraries of formalised mathematics required for this objective: higher-order derivatives and Taylor's theorem in Peano form. Finally, we qualitatively evaluate the use of the framework for verifying numerical methods.

cs.LO↗