Understanding directed temporal interactions in multivariate time series is essential for interpreting complex dynamical systems and the predictive models trained on them. We present Causal-INSIGHT, a model-agnostic, post-hoc interpretation framework for extracting model-implied (predictor-dependent), directed, time-lagged influence structure from trained temporal predictors. Rather than inferring causal structure at the level of the data-generating process, Causal-INSIGHT analyzes how a fixed, pre-trained predictor responds to systematic, intervention-inspired input clamping applied at inference time. From these responses, we construct directed temporal influence signals that reflect the dependencies the predictor relies on for prediction, and introduce Qbic, a sparsity-aware graph selection criterion that balances predictive fidelity and structural complexity without requiring ground-truth graph labels. Experiments across synthetic, simulated, and realistic benchmarks show that Causal-INSIGHT generalizes across diverse backbone architectures, maintains competitive structural accuracy, and yields significant improvements in temporal delay localization when applied to existing predictors.

翻译：理解多元时间序列中的有向时间交互对于解释复杂动态系统及其上训练的预测模型至关重要。我们提出Causal-INSIGHT，一个模型无关的后验解释框架，用于从已训练的时间预测器中提取模型隐含（依赖于预测器）的、有向的、带时间滞后的影响结构。不同于在数据生成过程层面推断因果结构，Causal-INSIGHT通过分析固定的预训练预测器在推理时对受干预启发的系统性输入钳制所作出的响应来工作。根据这些响应，我们构建反映预测器依赖关系的有向时间影响信号，并引入Qbic（一种具有稀疏感知性的图选择准则），它能在无需真实图标签的情况下平衡预测保真度与结构复杂性。在合成、模拟和现实基准上的实验表明，Causal-INSIGHT能泛化至多种骨干架构，保持有竞争力的结构准确性，并在应用于现有预测器时显著提升时滞定位性能。