arXiv 论文提出响应理论探针，检验随机 AI 模拟器对强迫的响应
A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63
这篇论文教你用线性响应理论给 AI 模拟器做体检，储备池计算机统计上看着挺对但响应错了，神经 ODE 反过来，挺反直觉。
arXiv 论文基于 Koopmanism Response 框架，提出一种校准的模式分辨检验，用于评估学习型代理模型对强迫的响应是否正确。研究在随机 Lorenz-63 系统上测试了 SINDy、MLP、储备池计算机、神经 ODE 和学习扩散的神经 SDE 五类模型，每类最多 80 次 rollout。结果显示不变统计保真度与响应保真度可双向分离：约四分之一的储备池计算机 rollout 通过全部不变统计检验并匹配静态磁化率 χ(0)，却错误表征慢弛豫模式，而神经 ODE 和 SDE 虽较少达到不变统计下限，却在四分之三的 rollout 中恢复这些模式。论文还发现训练公式（单步漂移、流映射或多步积分）决定固定网络获得哪种性质。
A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63
Machine-learning emulators of chaotic and stochastic systems are usually validated on forecast skill and long-run statistics. Neither certifies that an emulator responds correctly to forcing, the property that projection and attribution studies rely on. Linear response theory makes this testable: the forced response follows from unperturbed correlations through a generalized fluctuation-dissipation relation, and decomposes over the stochastic Ruelle-Pollicott resonances of the Koopman generator. Building on the Koopmanism Response framework, we turn this into a calibrated, mode-resolved test for learned surrogates: each surrogate rollout passes or fails each check, and failure rates are compared with those of independent realizations of the true system. On stochastic Lorenz-63, a three-variable toy model, we evaluate SINDy, an MLP, a reservoir computer, a neural ODE and a neural SDE with learned diffusion, over up to 80 rollouts each. A sparse-regression model with the correct library passes every check at rates consistent with the true system. Invariant-statistics fidelity and response fidelity dissociate in both directions: a quarter of reservoir-computer rollouts pass every invariant-statistics check and match the static susceptibility $χ(0)$, yet misrepresent the slow relaxation modes, while the neural ODE and SDE rarely meet the invariant-statistics floor but recover those modes in three quarters of rollouts. As expected of a time-integrated quantity dominated here by fast relaxation, $χ(0)$ does not separate these cases. For a fixed network, the training formulation (one-step drift, flow map, or multi-step through the integrator) decides which of these properties it gets right.
