proof-assistant

Tag

Cards List
#proof-assistant

Leanstral 1.5: Proof Abundance for All

Hacker News Top · 17h ago Cached

Mistral AI releases Leanstral 1.5, a 6B active parameter model for Lean 4 proof engineering, achieving state-of-the-art results on multiple formal verification benchmarks and uncovering real-world bugs, fully open-sourced under Apache-2.0.

0 favorites 0 likes
#proof-assistant

Reformalization of the Jordan Curve Theorem

arXiv cs.AI · yesterday Cached

This paper presents a case study in reformalization, transferring the Jordan Curve Theorem between proof assistants (Mizar to Lean, HOL Light to Lean and Agda) using LLMs, and analyzes pipeline design choices for practical reformalization.

0 favorites 0 likes
#proof-assistant

Proving the Fundamental Theorem of Arithmetic in Agda

Lobsters Hottest · 4d ago Cached

A detailed blog post presenting a fully commented proof of the Fundamental Theorem of Arithmetic in Agda, intended for intermediate learners of the proof assistant.

0 favorites 0 likes
#proof-assistant

VGPT-RSI for RH-Adjacent Formal Progress: Boundary Certificates, Verified Finite Lagarias Inequalities, and Explicit Failure Localization

arXiv cs.AI · 2026-06-16 Cached

This paper applies the VGPT-RSI AI system to produce formally verified partial results related to the Riemann Hypothesis, including boundary certificates and finite Lagarias inequalities, while explicitly identifying remaining mathematical obstructions.

0 favorites 0 likes
#proof-assistant

hax: A Rust verification tool

Lobsters Hottest · 2026-06-11 Cached

hax is a tool for translating Rust code into formal languages like F*, Rocq, and Lean for high-assurance verification.

0 favorites 0 likes
#proof-assistant

@FinanceYF5: Google new paper: Let LLM solve math competition problems, accuracy jumps from 10% to 70%. [LEAP framework] Instead of having the model write a complete proof at once, it breaks down the problem into a goal tree, learns step by step from Lean verifier feedback, and reuses proven lemmas. Result: All 12 problems of Putnam 2025 solved, IMO style…

X AI KOLs Timeline · 2026-06-05 Cached

Google new paper proposes the LEAP framework, which decomposes math problems into goal trees, learns from Lean verifier feedback, and improves LLM accuracy on math competition problems from 10% to 70%. It solves all 12 problems of Putnam 2025 and surpasses dedicated gold-medal-level systems on IMO-style benchmarks.

0 favorites 0 likes
#proof-assistant

A Formally Verified Library of Mathematical Finance in Lean 4

Hugging Face Daily Papers · 2026-05-31 Cached

This paper describes a formally verified library of mathematical finance in Lean 4, containing over 200 theorems covering measure-theoretic foundations through derivative pricing, and includes a faithfulness audit to classify results by how their Lean statement relates to the claimed mathematics.

0 favorites 0 likes
← Back to home

Submit Feedback