Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
Sachith X. S., Author 2, Author 3, Author 4, Author 5
Abstract
The paper introduces ConceptTime, a method for time-series classification that achieves accuracy, interpretability, and the ability to abstain from predictions when evidence is weak.
Reality Card
ConceptTime closes the circularity in defining meaningful temporal patterns and segment boundaries, achieving competitive accuracy with state-of-the-art methods while maintaining interpretability.
ConceptTime retains near-98% accuracy on Epilepsy with only 1% of labels across 17 public benchmarks.
The method's reliance on a frozen probabilistic forecaster may limit its adaptability to different domains without retraining.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.