Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.01008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910277063147520 |
|---|---|
| author | Dougherty, Quinn von Hippel, Max Shackleton, Hazel Dodds, Mike |
| author_facet | Dougherty, Quinn von Hippel, Max Shackleton, Hazel Dodds, Mike |
| contents | We present a benchmark for evaluating AI models and agents on real-world formal software verification tasks. We first scrape 11,039 property-based tests (PBTs) from real-world Python repositories, then automatically translate 2,772 of them (25%) into 9,415 Lean 4 specifications with sorry placeholders (about 3 formalizations/PBT; we retain multiple attempts when none dominates on quality metrics). Translating PBTs into Lean specifications is challenging: it requires modeling Python semantics in Lean, inferring the logical property encoded in an imperative PBT, and handling the inherent difficulties of dependently-typed programming in a seldom-used language. We describe a three-agent LLM pipeline for transpiling PBTs into Lean specifications, evaluate coverage and quality metrics, and provide baselines for proof generation using several automated and model based approaches. All code (scraper and agents) and data (PBTs and Lean specifications) are open source. Our benchmark aims to drive progress on the underexplored problem of AI-assisted formal verification of real-world software, which is of increasing interest as AI produces more and more of the world's code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01008 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FVSpec: Real-World Property-Based Tests as Lean Challenges Dougherty, Quinn von Hippel, Max Shackleton, Hazel Dodds, Mike Software Engineering Artificial Intelligence We present a benchmark for evaluating AI models and agents on real-world formal software verification tasks. We first scrape 11,039 property-based tests (PBTs) from real-world Python repositories, then automatically translate 2,772 of them (25%) into 9,415 Lean 4 specifications with sorry placeholders (about 3 formalizations/PBT; we retain multiple attempts when none dominates on quality metrics). Translating PBTs into Lean specifications is challenging: it requires modeling Python semantics in Lean, inferring the logical property encoded in an imperative PBT, and handling the inherent difficulties of dependently-typed programming in a seldom-used language. We describe a three-agent LLM pipeline for transpiling PBTs into Lean specifications, evaluate coverage and quality metrics, and provide baselines for proof generation using several automated and model based approaches. All code (scraper and agents) and data (PBTs and Lean specifications) are open source. Our benchmark aims to drive progress on the underexplored problem of AI-assisted formal verification of real-world software, which is of increasing interest as AI produces more and more of the world's code. |
| title | FVSpec: Real-World Property-Based Tests as Lean Challenges |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2606.01008 |