这篇论文用受控实验证明，模型输出能藏住内部状态的证据，128对测试全过，对理解AI可解释性挺有意思。
该研究探讨语言模型输出能否携带可验证的内部计算证据。在模块化前馈网络和Transformer两种架构上，用算术任务训练模型，使其经过两个离散中间状态。系统在128对匹配测试中全部通过，检测器成功恢复认证内部状态信号。五个前馈模型和三个Transformer模型均复现了因果计算。单独答案实验中，线性探针未能恢复自然学习的中间状态。
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
A language model's output does not by itself provide verifiable evidence about the internal computation that produced it. We study computational provenance: whether generated text can carry detectable evidence of which causally relevant internal state occurred. We test a bounded form of this idea in two controlled architectures: a modular feed-forward neural network and a transformer-based model. Both architectures are trained on the same arithmetic task with a mandatory pathway through two discrete intermediate states, allowing different internal paths to produce the same answer. We deliberately switch between these paths, authenticate the state actually used, and let that verified state determine a subtle statistical pattern in the generated text that can later be detected. The feed-forward and transformer systems each passed all 128 matched pairs in both their public and separately sealed protected end-to-end evaluations, with the detector recovering the signal associated with the authenticated internal state. The required causal computation also reproduced across five independently trained feed-forward models and three independently trained transformers. In a separate answer-only transformer experiment, our linear probes did not recover a naturally learned intermediate state. These results provide a controlled proof of concept that information about a verified, causally relevant internal state can be preserved in generated text even when the answer is unchanged.