Surrogate models for topology optimization (TO) exhibit highly variable out-of-distribution (OOD) generalization under distribution shifts such as changing loads or boundary conditions, yet the source of this variability remains unclear. We hypothesize that OOD performance is governed by how much information the conditioning signal preserves about the adjoint sensitivity (reduced gradient) that drives classical TO. Modeling the TO pipeline as a causal Markov chain, the Data Processing Inequality establishes that, under this abstraction, the sensitivity field is an information-theoretically optimal conditioning signal for topology prediction. However, computing exact adjoint sensitivities can be expensive or unavailable in practice; we observe that certain physical fields can approximate sensitivities through monotone transformations. To formalize this, we introduce \textbf{pseudo-sensitivities} to characterize which fields enable generalization versus those that are information-poor. We then show that a sensitivity-conditioned Bernoulli flow-matching generator empirically confirms these predictions: conditioning on sensitivities yields state-of-the-art OOD performance, while increasingly distant physical fields degrade toward raw parameter conditioning. Results hold across structural TO benchmarks under load shifts and our new CFD-TO dataset under boundary-condition shifts such as multi-outlet configurations. Code and datasets are available at https://tum-pbs.github.io/topotransformer/ .

翻译：拓扑优化（TO）的代理模型在分布偏移（如载荷或边界条件变化）下表现出高度可变的分布外（OOD）泛化性能，但这种可变性的来源尚不明确。我们假设OOD性能取决于条件信号保留关于驱动经典TO的伴随灵敏度（简化梯度）的信息量。将TO管线建模为因果马尔可夫链时，数据处理不等式表明，在此抽象下，灵敏度场是拓扑预测中信息论最优的条件信号。然而，计算精确的伴随灵敏度在实践中可能代价高昂或不可行；我们观察到某些物理场可以通过单调变换近似灵敏度。为形式化这一概念，我们引入**伪灵敏度**来表征哪些场能实现泛化，而哪些场信息贫乏。我们随后证明，基于灵敏度条件的伯努利流匹配生成器在实验上验证了这些预测：以灵敏度为条件可实现最先进的OOD性能，而距离较远的物理场条件性能逐渐退化为原始参数条件。该结果在载荷变化的结构TO基准测试以及我们提出的多出口配置等边界条件变化的CFD-TO数据集上均成立。代码和数据集见https://tum-pbs.github.io/topotransformer/。