Theoria 能审计 AI 回答的每一步推理，HLE 上精度 91.4%，比纯 LLM 评判更可追溯，专治隐藏前提和伪造引用。
Theoria 是一种验证架构，将候选解答重写为一系列类型化状态转换，每步转换需提供明确理由（引用、计算或给定事实），且可独立审计。在 HLE-Verified Gold（185 道文本专家题）上，Theoria 认证了 105 题，严格精度达 91.4%（Wilson 95% CI [84.5%, 95.4%]）。与整体 LLM 评判者相比，两者错误分布差异大（Jaccard 0.14-0.36），可互补。在 95 个对抗性有毒证明上，结构评判者捕获 94.7%，高于整体评判的 83.2%（p=0.0017）。在 GPQA Diamond（n=65）上，认证精度为 97.1%。
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judges offer coverage but produce opaque scores that cannot be audited after the fact and are subject to the same coherence issues as any LLM. We present Theoria, a verification architecture that closes this gap. A candidate solution is rewritten into a sequence of typed state transitions, each licensed by an explicit justification, whether that be a citation, computation, or problem-given fact, and every transition is independently auditable. The foundational invariant is completeness of change: every difference between consecutive proof states must be accounted for, so hidden premises surface as unlicensed mutations rather than passing silently. On HLE-Verified Gold (185 text-only expert problems), Theoria certifies 105 at 91.4% strict precision (Wilson 95% CI [84.5%, 95.4%]). Every certification produces a human readable proof trace in which each step can be independently challenged. Holistic LLM judges achieve comparable precision at matched coverage but fail on different problems (Jaccard 0.14-0.36), making the approaches complementary. On 95 adversarial poisoned proofs across 15 domains, structured judges catch 94.7% versus 83.2% for holistic judging (p= 0.0017). The overall 11.5 pp gap concentrates in hidden premises (90.6% vs. 62.5%, a 28 pp difference) and fabricated citations (100% vs. 90%), the error classes where the formal analysis predicts an advantage; performance is identical on arithmetic and theorem-misapplication errors, where no advantage is predicted. On GPQA Diamond (n= 65), certified precision is 97.1% (Wilson CI [85.1%, 99.5%]).