arXiv AI

Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series

The paper introduces ConceptTime, a time‑series classifier that achieves accuracy, interpretability, and abstention by using a self‑supervised predictive surprise signal. A frozen probabilistic forecaster generates predictions at each timestep; the mismatch between prediction and actual observation identifies segment boundaries and defines concepts that describe each segment’s dynamics. ConceptTime’s lightweight head classifies from these concepts, and the distance to the nearest concept provides a built‑in reliability measure, achieving state‑of‑the‑art performance across 17 benchmarks without requiring annotations or expert input.

arXiv AI
Oct 12

KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting

KITE is a knowledge‑injected temporal encoder that augments self‑supervised event forecasting with semantic priors supplied by system engineers. It uses two switchable mechanisms—a covariate mechanism and an attention‑bias mechanism—so the same architecture can incorporate different prior types without per‑dataset tuning. Experiments show that informative priors improve performance in short contexts and enable out‑of‑domain transfer, while priors already present in the observed window have little effect.

By Jonas Petersen, Pratik Jawahar, Riccardo Maggioni, Gian-Alessandro Lombardi, Matteo Cozzi, Marek Gajewski, Federico Martelli, Camilla Mazzoleni, Philipp Christian Petersen
arXiv Machine Learning
Jul 2

LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning

arXiv:2607. 00958v1 Announce Type: new Abstract: Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances.

By Alexander Chemeris, Ming Jin, Randall Balestriero
arXiv AI
Nov 6

Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER

The paper benchmarks two frozen forecasting models, Reverso and Chronos‑Bolt, as feature extractors for time‑series classification on the MONSTER dataset. Using 1%, 10%, and 100% of training labels, the authors compare the models’ frozen representations to four established classifiers and to random‑weight versions of the same models. Results show that pretraining yields higher accuracy than random weights on five of six datasets, but the frozen representations never outperform the best non‑pretrained baseline, performing worse in 15 of 17 settings and tying only twice.

By Rishit Jain, Rishit Kar, Chetashri Bhadane, Nilesh Patil