发表机构
California Institute of Technology; NVIDIA; Institute of Science Technology Austria（加州理工学院; 英伟达; 奥地利科学技术研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ReRoute框架，结合事实数据与部分机制知识，无需受控实验即可在科学仿真器中实现高精度反事实预测，并在气候仿真中显著降低误差。
AI 中文摘要
许多科学问题需要对从未观测到的情形进行推理：如果条件、干预或历史有所不同会怎样？模型在观测数据上可以准确预测，但当相关输入被独立变化时，这类“如果”查询却可能失败。常见的补救措施是添加受控模拟数据，在这些数据中这些因素被明确解耦，但这需要访问模拟器，计算成本可能很高，并且继承了模拟器的建模假设。我们提出了ReRoute，一个用于针对性科学“如果”预测的框架，它将事实数据与部分机制性知识相结合，无需受控干预数据即可进行适应。ReRoute将预训练骨干网络的查询输入固定为参考值，通过已知的机制路径重新引入其变化，并在原始事实数据上进行微调，同时将下游效应留给学习到的动力学。我们在明确的结构假设下为这种构造提供了因果识别结果，核心论证在Lean中进行了机器验证。在展示ReRoute在受控对流-扩散系统中实现高度准确的反事实预测（其中可获得精确响应）之后，我们转向最先进的气候仿真。在保留的耦合气候干预上，ReRoute在严重的CO$_2$分布偏移下将聚合气候误差降低了18.2%-31.8%，同时在标准条件下保持技能，其成本仅为在额外受控模拟上重新训练的一小部分，甚至不考虑生成此类数据的巨额费用。最后，在从历史ERA5再分析数据训练的仿真器上（不存在反事实参考），ReRoute在固定CO$_2$反事实下保留了由观测边界条件所隐含的地表变暖的显著更多部分。
英文摘要
Many scientific questions require reasoning about what was never observed: What if the conditions, interventions, or history had been different? Models can predict accurately on observed data yet fail on such what-if queries when correlated inputs are varied independently. A common remedy is to add controlled simulation data in which these factors are explicitly disentangled, but this requires access to a simulator, can be computationally expensive, and inherits the simulator's modeling assumptions. We introduce ReRoute, a framework for targeted scientific what-if prediction that combines factual data with partial mechanistic knowledge, without requiring controlled intervention data for adaptation. ReRoute fixes the queried input of a pretrained backbone to a reference value, reintroduces its variation through a known mechanistic pathway, and fine-tunes on the original factual data, while leaving downstream effects to the learned dynamics. We provide a causal identification result for this construction under explicit structural assumptions, with the core argument machine-checked in Lean. After showing that ReRoute achieves highly accurate counterfactual predictions in a controlled advection-diffusion system where exact responses are available, we turn to state-of-the-art climate emulation. On held-out coupled-climate interventions, ReRoute reduces aggregate climate error by 18.2-31.8% under severe CO$_2$ distribution shifts while preserving skill under standard conditions, at a small fraction of the cost of retraining on additional controlled simulations, without even accounting for the substantial expense of generating such data. Finally, on an emulator trained from historical ERA5 reanalysis, where no counterfactual reference exists, ReRoute preserves substantially more of the surface warming implied by the observed boundary conditions under a fixed-CO$_2$ counterfactual.
