On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models

arXiv:2610.13676 · cs.LG · Submitted 2026-10-09 · Read on arXiv

cs.LG

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/google-research/timesfm

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes

Sources

• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
• Chronos: Learning the Language of Time Series
• Chronos-2: From Univariate to Universal Forecasting
• TFMAdapter: Lightweight Instance-Level Adaptation of Foundation Models for Forecasting with Covariates
• MOMENT: A Family of Open Time-series Foundation Models
• TabPFN-3: Technical Report
• UniCA: Unified Covariate Adaptation for Time Series Foundation Model
• A Benchmark for Electrical Load Forecasting Across Grid Levels: Time-Series Transformers Outperform Established Methods
• LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction
• Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics
• Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting
• A Unified Approach to Interpreting Model Predictions
• t 0: A Time-Series Foundation Model for Forecasting with Context
• Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges
• Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence
• Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features
• CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
• fev-bench: A Realistic Benchmark for Time Series Forecasting

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks