<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Credible-Compilation on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/credible-compilation/</link><description>Recent content in Credible-Compilation on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Sun, 04 Oct 2026 12:20:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/credible-compilation/index.xml" rel="self" type="application/rss+xml"/><item><title>019 · 编译器被证明正确，错误还藏在哪里？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-10-04/</link><pubDate>Sun, 04 Oct 2026 12:20:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-10-04/</guid><description>ACDC 以 Axon 为对象，分别测试已验证核心、可信检查、未验证文本接口与机器语义；实验说明形式证明能封闭一部分错误，却不能替代对规格、信任边界和拒绝行为的测试。</description></item></channel></rss>