From Signals to Semantics: A Survey on Time Series Explainability through a Human-Cognitive Lens

Machine learning and deep learning have demonstrated remarkable success across a wide range of time series tasks. However, their lack of transparency limits explainability and trust. To address this challenge, numerous explanation methods have been proposed in recent years, each of them providing distinct perspectives on how to interpret time series models through signals, patterns, structures, or semantics. This survey synthesizes these perspectives into a unified cognitive hierarchy that bridges methodological diversity with human understanding. Existing approaches are classified into four levels: signal-space, pattern-space, structural, and semantic, reflecting a progressive shift from low-level signal attribution to high-level semantic reasoning. Building on this taxonomy, we conduct comprehensive literature review, revealing cross-level connections, emerging trends, and critical gaps in current research. Our analysis underscores the growing importance of semantic explanations, particularly those facilitated by large language models (LLMs), as a promising direction for achieving human-centered and readable explainability. In addition, we compile and categorize data benchmarks used for explaining diverse time series tasks and provide an accompanying open repository to support continued research in this field.