arXiv:2606. 09473v1 Announce Type: cross Abstract: Probabilistic forecasters are increasingly learned, yet the baselines they are compared against are often weak or omitted.
The paper introduces a learned atmospheric critic that discriminates between real weather data and model outputs to produce a realism score. Unlike fixed metrics, the discriminator adapts to the specific failure modes of a given model, effectively detecting various synthetic corruptions in ERA5 data. Experiments show the learned critic outperforms existing metrics and reveals that realism decreases with longer forecast lead times, favoring numerical over machine‑learning models.
arXiv:2606. 29661v1 Announce Type: new Abstract: Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding.
arXiv:2607. 28124v1 Announce Type: new Abstract: As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves.
Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding. We study how to improve this recipe through ensembling: given a fixed number of samples, which off-the-shelf model forecasts should be combined to maximize accuracy?
Deep learning methods have achieved state-of-the-art in time series forecasting, yet their accuracy varies considerably across samples, as some instances remain inherently difficult to predict. Reject option mechanisms, which allow models to abstain from high-risk predictions, are well established in classification and regression but underexplored in forecasting.
arXiv:2607. 23165v1 Announce Type: cross Abstract: We propose ABF-T-GLCP, a model-agnostic framework for forecasting and uncertainty quantification in nonstationary multivariate time series.
SPACE is a conformal wrapper that creates ellipsoidal joint prediction regions for multivariate time‑series forecasts by estimating time‑local covariance directly from the current forecast sample cloud. It calibrates the region’s radius using a dynamic backward window‑selection scheme, avoiding reliance on historical residuals. Experiments on diverse datasets show that SPACE improves joint and rolling coverage, achieving better coverage‑efficiency tradeoffs than existing wrappers.
arXiv:2608.20406v1 Announce Type: new Abstract: Public health forecasts must respond to abrupt changes in surveillance data without over-extrapolating noise, reporting artifacts, or temporary trends....
arXiv:2608. 10553v1 Announce Type: cross Abstract: Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often inefficient for time series data, where forecast errors are temporally dependent and change across time and operating conditions.
Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often inefficient for time series data, where forecast errors are temporally dependent and change across time and operating conditions. Recent time series CP methods improve local calibration using recent, weighted, or localized residuals.
arXiv:2601. 14031v2 Announce Type: replace-cross Abstract: Forecasting intermittent time series, which contain zeros, is a crucial challenge in supply chains as inventory policies require probabilistic forecasts to establish safety levels.