We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this as the Determinism Thesis and introduce trust entropy to quantify the cost of non-determinism, proving that verification failure probability equals 1 - 2^{-H_T} exactly. We prove a Determinism-Verification Collapse: verification under determinism requires O(1) hash comparison; without it, the verifier faces an intractable membership problem. IEEE 754 floating-point arithmetic fundamentally violates the determinism requirement. We resolve this by constructing a pure integer inference engine that achieves bitwise identical output across ARM and x86. In 82 cross-architecture tests on models up to 6.7B parameters, we observe zero hash mismatches. Four geographically distributed nodes produce identical outputs, verified by 356 on-chain attestation transactions. Every major trust property of AI systems (fairness, robustness, privacy, safety, alignment) presupposes platform determinism. Our system, 99,000 lines of Rust deployed across three continents, establishes that AI trust is a question of arithmetic.

翻译：我们证明，平台确定性推理是可信赖人工智能的必要且充分条件。我们将此形式化为“确定性论题”，并引入信任熵来量化非确定性的代价，精确证明验证失败概率等于1-2^{-H_T}。我们证明了“确定性-验证坍缩”：在确定性条件下，验证只需O(1)次哈希比较；而在非确定性条件下，验证器面临棘手的成员问题。IEEE 754浮点运算从根本上违反了确定性要求。我们通过构建一个纯整数推理引擎来解决此问题，该引擎在ARM和x86架构上实现了比特级一致输出。在针对高达6.7B参数模型的82项跨架构测试中，我们观察到零哈希不匹配。四个地理分布的节点产生相同的输出，并由356次链上证明交易验证。人工智能系统的每一项核心可信赖属性（公平性、鲁棒性、隐私性、安全性、对齐）都以平台确定性为前提。我们的系统由99,000行Rust代码构成，部署在三大洲，确立了人工智能可信赖本质上是算术问题这一结论。