Reproduce “Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sachith Abeywickrama, Emadeldeen Eldele, Min Wu, Xiaoli Li, Chau Yuen
ConceptTime uses a frozen self-supervised forecaster to guide segmentation and represent segments with predictive statistics. Surprise helps set patch boundaries, while clustered signatures form concepts for classification; prototype distance measures coverage of that vocabulary. On UCI-HAR, predictive moments achieve 87.7% accuracy versus 42.7% for raw-signal morphology with patches fixed, a result limited to that setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.