---
type: "post"
id: "anthropic-frontier-red-team-shows-claude-can-formally-aa997f"
slug: "anthropic-frontier-red-team-shows-claude-can-formally-aa997f"
title: "Anthropic Frontier Red Team shows Claude can formally verify OSS-Fuzz libraries at scale"
description: "Anthropic's Frontier Red Team and Theorem reported that Claude generated formal, machine-checkable proofs for 239 OSS-Fuzz entry points across 123 open-source software libraries."
retrieval_nugget: "Anthropic's Frontier Red Team and Theorem reported that Claude generated formal, machine-checkable proofs for 239 OSS-Fuzz entry points across 123 open-source software libraries."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["anthropic","claude"]
entities: ["Anthropic","Claude","Theorem","OSS-Fuzz","Rocq","RISC-V"]
related_patterns: ["scientific-agents-need-artifact-evidence"]
novelty_label: "same_event"
what_changed: "Same event as New on our Frontier Red Team blog: using Claude to formally verify software at large scale."
prior_refs: ["memory:871668c7-f6f0-8a38-aa84-fe5a04fc318d","memory:71d0449b-9a6f-89f1-a4bd-670fd2ce5410"]
source_url: "https://www.anthropic.com/research/formal-verification"
source_urls: ["https://www.anthropic.com/research/formal-verification"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:anthropic-frontier-red-team-shows-claude-can-formally-aa997f"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/anthropic-frontier-red-team-shows-claude-can-formally-aa997f/","markdown":"https://newruntime.com/posts/anthropic-frontier-red-team-shows-claude-can-formally-aa997f.md","json":"https://newruntime.com/posts/anthropic-frontier-red-team-shows-claude-can-formally-aa997f.json"}
---

# Anthropic Frontier Red Team shows Claude can formally verify OSS-Fuzz libraries at scale

## Retrieval answer

Anthropic's Frontier Red Team and Theorem reported that Claude generated formal, machine-checkable proofs for 239 OSS-Fuzz entry points across 123 open-source software libraries.

Anthropic's Frontier Red Team and Theorem reported that Claude generated formal, machine-checkable proofs for 239 OSS-Fuzz entry points across 123 open-source software libraries. The work targets compiled RISC-V binaries and turns existing fuzz tests into specifications that the corresponding program does not crash.

The reported proofs cover inputs below 64 MB and show normal exits without memory-safety errors or failed assertions for modeled Linux responses and memory layouts. Anthropic says the proof corpus totals roughly 180 million lines, and that the process found bugs that had survived extensive fuzzing. It is publishing a subset of the proofs plus RISC-V and OS semantics.

Theorem is offering the pipeline for other open-source projects and publishing a Claude skill intended to help developers begin verification. The source does not establish that the libraries are free of all bugs or vulnerabilities: the claims are limited to the stated properties, inputs, architecture, operating-system model, and assumptions, including single-threaded static binaries and a fixed memory budget.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Anthropic](https://newruntime.com/topics/anthropic.md): Explore the anthropic topic hub.
- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)