---
id: "nr-machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a"
slug: "machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a"
type: "raw_signal"
title: "Machine-checked proofs are starting to replace tests and judges as the check on AI output"
description: "SWE-Proof checks patches for 500 real software issues with machine-verified proofs instead of relying only on test suites."
observed_at: "2026-11-22"
record_date: "2026-11-22"
date_kind: "observed_at"
novelty: "notable"
source_platform: "newruntime.com"
topics: ["claude"]
entities: ["SWE-Proof","Benchproofer","Claude Opus 4.8","SWE-bench Verified","SWE-bench Pro","Amazon","AutoCorrode","Isabelle","I/Q","I/R"]
related_patterns: ["scientific-agents-need-artifact-evidence"]
source_url: "https://arxiv.org/abs/2609.21190"
source_urls: ["https://arxiv.org/abs/2609.21190","https://www.amazon.science/blog/mathematical-proof-powered-by-ai-and-no-hallucinations","https://leanprover-community.github.io/blog/posts/riemann-hypothesis"]
why_it_matters: "SWE-Proof checks patches for 500 real software issues with machine-verified proofs instead of relying only on test suites. Amazon released tools that connect agents to the Isabelle proof assistant, and the Lean and Mathlib communities certified a formal proof of the Riemann Hypothesis after several independent checks. Where a formal statement exists, agent output can be accepted on proof rather than on a grader's opinion."
verification_level: "source-linked"
signal_type: "synthesis"
synthesis_of: [{"slug":"swe-proof-turns-500-real-software-issues-into-3e10e9","title":"SWE-Proof turns 500 real software issues into a benchmark where patches are checked with machine-verified","url":"https://newruntime.com/posts/swe-proof-turns-500-real-software-issues-into-3e10e9/"},{"slug":"mathematical-proof-powered-by-ai-and-no-hallucinations-319bff","title":"Mathematical proof, powered by AI. And no hallucinations!","url":"https://newruntime.com/posts/mathematical-proof-powered-by-ai-and-no-hallucinations-319bff/"},{"slug":"lean-verification-of-the-riemann-hypothesis-b2c2b2","title":"Lean verification of the Riemann Hypothesis","url":"https://newruntime.com/posts/lean-verification-of-the-riemann-hypothesis-b2c2b2/"}]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a"
retrieval_nugget: "SWE-Proof checks patches for 500 real software issues with machine-verified proofs instead of relying only on test suites. Amazon released tools that connect agents to the Isabelle proof assistant, and the Lean and Mathlib communities certified a formal proof of the Riemann Hypothesis after several independent checks."
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/signals/machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a/","markdown":"https://newruntime.com/signals/machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a.md","json":"https://newruntime.com/signals/machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a.json"}
markdown_url: "https://newruntime.com/signals/machine-checked-proofs-are-starting-to-replace-tests-and-judges-as-the-8d2c4a.md"
---

# Machine-checked proofs are starting to replace tests and judges as the check on AI output

## Retrieval answer

SWE-Proof checks patches for 500 real software issues with machine-verified proofs instead of relying only on test suites. Amazon released tools that connect agents to the Isabelle proof assistant, and the Lean and Mathlib communities certified a formal proof of the Riemann Hypothesis after several independent checks.

SWE-Proof checks patches for 500 real software issues with machine-verified proofs instead of relying only on test suites. Amazon released tools that connect agents to the Isabelle proof assistant, and the Lean and Mathlib communities certified a formal proof of the Riemann Hypothesis after several independent checks. Where a formal statement exists, agent output can be accepted on proof rather than on a grader's opinion.

From the Field Notes:

- [SWE-Proof turns 500 real software issues into a benchmark where patches are checked with machine-verified](https://newruntime.com/posts/swe-proof-turns-500-real-software-issues-into-3e10e9/) (2026-11-21)
- [Mathematical proof, powered by AI. And no hallucinations!](https://newruntime.com/posts/mathematical-proof-powered-by-ai-and-no-hallucinations-319bff/) (2026-11-21)
- [Lean verification of the Riemann Hypothesis](https://newruntime.com/posts/lean-verification-of-the-riemann-hypothesis-b2c2b2/) (2026-11-22)

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: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- collection: [Signals](https://newruntime.com/signals.json): Open the signals and the raw-signal archive.
- collection: [Sources](https://newruntime.com/sources/): See the original sources this archive cites.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)
