COunterfactual Reasoning for Temporal EXplanations: Plausible and Robust Explanations for EEG-Based Seizure Detection

Identifying the drivers of change in time-sensitive domains like healthcare is critical for reliable decision-making, yet explanations must account for both temporal dynamics and structural complexity. While counterfactual explanations are well-studied for static data, existing methods often fail in dynamic, spatio-temporal settings, producing implausible or temporally inconsistent explanations. To address this, we introduce COunterfactual Reasoning for Temporal EXplanations (CORTEX), a search-based explainer for multivariate time series modeled as spatio-temporal graphs, tailored to binary seizure detection from EEG recordings. CORTEX generates temporally robust and plausible counterfactuals by retrieving relevant past instances and sieving them via structural dissimilarity, temporal distance, and robustness. As a result of its design choices, when evaluated on clinical seizure detection data, CORTEX outperforms state-of-the-art methods by 3.73x in validity and 6.32x in fidelity, and achieves zero implausibility, demonstrating consistency and practical relevance. By shifting the focus from mere validity to plausible, time-consistent explanations, CORTEX enables more reliable, controllable counterfactual explanations.