# GRAIL: From Saliency to Semantics in Time-Series Explanation

**Published:** October 22, 2026
**Author:** Enver Menadjiev, Yiqiu Shen, Jaesik Choi, Julia Stoyanovich
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/grail-from-saliency-to-semantics-in-time-series-explanation

arXiv:2610.29036v1 Announce Type: new Abstract: Explaining a time-series model requires both locating the evidence and extracting meaningful knowledge from it. Yet a single timestep is not a semantic unit: the meaningful patterns live across many samples, not in any one of them.…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.29036)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*