SHAP for Time Series Foundation Models
SHAP for Time Series Foundation Models
Auto-generated stub. Edit this file to add more details.
An algorithm for computing SHAP values for time series foundation models by exploiting their inherent flexibility in input context length and covariate handling.
Why It Matters
Addresses the critical need for explainability in black-box foundation models applied to high-stakes infrastructure like power grids.
Evidence
propose an efficient algorithm for computing Shapley Additive Explanations (SHAP) tailored to these models. The proposed approach leverages the flexibility of TSFMs with respect to input context length and provided covariates.
Related Papers
Metadata & Links
- created_at
- 2026-05-03T06:02:28Z