More capable LLMs produce worse distributional forecasts on superlinear growth time series with tail risks of regime change, with the error concentrated in the upper tail; this reverses on conventional threshold metrics.
Transactions on Machine Learning Research , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 5roles
method 1polarities
use method 1representative citing papers
Regime-stratified evaluation on traffic benchmarks shows TSFM accuracy and interval coverage collapse during transitions (MAE 11 mph vs 3 mph overall; coverage to 55%), hidden by free-flow dominance, with BMA augmentation recovering transition coverage.
PULSE is a physics-informed plug-and-play framework that uses phase-anchored disentanglement, a Phase Router, and statistic-aware mixup to mitigate Phase Amnesia in non-stationary forecasting and achieve strong results with simple backbones.
Ensemble models using only satellite SST, upwelling, chlorophyll-a and PFTs predict Pseudo-nitzschia HAB occurrence at ROC–AUC 0.77±0.06 under year×cluster cross-validation on the Portuguese L1–L2 coast.
A frozen average of the last two cycles matches or exceeds eight shape-learning alternatives on 97 GIFT-Eval configurations for periodic time series forecasting.
citing papers explorer
-
Don't Learn the Shape: Forecasting Periodic Time Series by Rank-1 Decomposition
A frozen average of the last two cycles matches or exceeds eight shape-learning alternatives on 97 GIFT-Eval configurations for periodic time series forecasting.