Reproduce “Ripple: An Open, AI-Formalized Lean 4 Framework for Computing with CRNs” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Ho-Lin Chen, Xiang Huang

Researchers developed Ripple, an open, AI-formalized Lean 4 framework comprising 768,000 lines of code, for computing with Chemical Reaction Networks (CRNs). This framework unifies CRN computational models, machine-checks the computability of various real numbers including Apéry's constant ζ(3), and verifies Turing completeness results, while also identifying gaps in existing proofs.

Key insights

  • Formalization with Lean 4 effectively uncovered subtle gaps and unstated assumptions in established CRN computation literature.
  • Publicly available AI agents can autonomously perform large-scale, high-quality formalization of complex mathematical theories.
  • The process of formal verification clarifies the distinction between arbitrary precision approximation and exact computation for constants like ζ(3) and π.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.