Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
cs.LG, cs.AI, eess.SP, stat.ML
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/Sachithx/ConceptTime
Terminology
Sources
- Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
- The UEA multivariate time series classification archive, 2018
- Towards Interpretable Concept Learning over Time Series via Temporal Logic Semantics
- Learn to explain yourself, when you can: Equipping Concept Bottleneck Models with the ability to abstain on their concept predictions
- Do Concept Bottleneck Models Learn as Intended?
- Interpretability for Time Series Transformers using A Concept Bottleneck Framework
- Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction
- Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis