arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.20082cs.PL
收藏

机器生成、机器验证的证明用于验证编译器(经验报告)

Machine-Generated, Machine-Checked Proofs for a Verified Compiler (Experience Report)

National Technical University of Athens(雅典国立技术大学)

Zoe Paraskevopoulou

AI总结:

利用机器学习模型生成并验证编译器正确性证明,通过模板技术实现ANF转换的语义保持性证明,耗时96小时完成,展示了机器辅助证明的潜力与局限。

摘要:

我们报告了使用一个代理编码助手(Claude Code,由Claude Opus 4.6驱动)从头开始机械化一个相当规模的Rocq正确性证明,有人类指导但没有人类证明写作。该证明确立了行政正常形式(ANF)转换在CertiCoq验证编译器中的语义保持性。与之密切相关但相关的延续传递风格(CPS)转换在CertiCoq中之前由人类专家在几个月内证明正确。我们使用这个证明作为模板,并指示LLM将证明技术适应到ANF设置中,这在技术上有重要不同。所得到的ANF证明大约包含7,800行Rocq(比5,300行CPS证明更大),并在大约96小时内开发完成。我们描述了证明技术,并报告了与LLM开发它的经验,讨论了这种方法的优缺点及其对验证编译器构造的影响。

英文摘要:

We report on using an agentic coding assistant (Claude Code, powered by Claude Opus 4.6) to mechanize a substantial Rocq correctness proof from scratch, with human guidance but without human proof writing. The proof establishes semantic preservation for the administrative normal form (ANF) transformation in the CertiCoq verified compiler for Rocq. The closely related continuation-passing style (CPS) transformation in CertiCoq was previously proved correct by human experts over several months. We use this proof as a template and instruct the LLM to adapt the proof technique to the ANF setting, which differs in important technical ways. The resulting ANF proof comprises approximately 7,800 lines of Rocq (larger than the 5,300-line CPS proof) and was developed in approximately 96 hours. We describe the proof technique and report on the experience of developing it with an LLM, discussing both the strengths and limitations of the approach and its implications for verified compiler construction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑