Electroencephalography (EEG) is a cornerstone of brain-computer interfaces and clinical neuroscience, yet deep learning models are typically trained and evaluated under a single, unreported preprocessing pipeline. We formalize preprocessing choices as a counterfactual intervention space and show that EEG predictions are surprisingly unstable under this space: across six datasets spanning four paradigms, up to 42% of trial-level predictions flip when only the preprocessing changes, a variability that standard uncertainty methods do not explicitly quantify because they condition on a fixed preprocessing pipeline. We provide three tools to make this instability measurable, decomposable, and reducible. First, a Walsh-Hadamard decomposition of the 2^7 pipeline space reveals that sensitivity is near-additive in practice under the binary intervention design, enabling efficient step-by-step optimization. Second, we introduce Preprocessing Uncertainty (PU), a per-trial diagnostic that captures a dimension of instability complementary to model-based confidence. Third, we study Normalized Adaptive PGI (NA-PGI), a graph-structured regularizer that exploits the compositional structure of preprocessing interventions as one mitigation strategy with clear scope conditions.

翻译：脑电图（EEG）是脑机接口和临床神经科学的基石，但深度学习模型通常在单一且未报告的预处理流程下进行训练和评估。我们将预处理选择形式化为一个反事实干预空间，并证明在此空间下，脑电图预测惊人地不稳定：在涵盖四个范式的六组数据集中，仅改变预处理即可导致高达42%的试次级预测翻转，而标准不确定性方法因预设固定预处理流程而无法明确量化此类变异性。我们提供三种工具使该不稳定性可测量、可分解且可降低。首先，利用Walsh-Hadamard对2^7种预处理流程空间进行分解，揭示在二元干预设计下敏感性在实践中呈现近可加性，从而实现逐步高效优化。其次，引入预处理不确定性（Preprocessing Uncertainty, PU），这是一种与基于模型的置信度互补的不稳定性维度诊断指标。最后，我们研究归一化自适应PGI（NA-PGI）——一种图结构正则化器，其利用预处理干预的组合结构作为具有明确适用条件的缓解策略。