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

arXiv: https://arxiv.org/abs/2610.13676 · HTML: https://mlsanity.com/paper/2610.13676/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation](https://mlsanity.com/paper/2410.10393/) (2024)
- [TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning](https://mlsanity.com/paper/2505.23719/) (2025)
- [fev-bench: A Realistic Benchmark for Time Series Forecasting](https://mlsanity.com/paper/2509.26468/) (2025)
- [From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting](https://mlsanity.com/paper/2501.02945/) (2025)
- [Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features](https://mlsanity.com/paper/2104.00629/) (2021)
- [LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction](https://mlsanity.com/paper/2304.14343/) (2023)
- [Review of automated time series forecasting pipelines](https://mlsanity.com/paper/2202.01712/) (2022)
- [Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges](https://mlsanity.com/paper/2510.13654/) (2025)
- [TiRex-2: Generalizing TiRex to Multivariate Data and Streaming](https://mlsanity.com/paper/2607.01204/) (2026)
- [UniCA: Unified Covariate Adaptation for Time Series Foundation Model](https://mlsanity.com/paper/2506.22039/) (2025)
- [CoRA: Covariate-Aware Adaptation of Time Series Foundation Models](https://mlsanity.com/paper/2510.12681/) (2025)
- [Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models](https://mlsanity.com/paper/2604.28149/) (2026)
- [Modelling and forecasting daily electricity load curves: a hybrid approach](https://mlsanity.com/paper/1611.08632/) (2016)
- [TFMAdapter: Lightweight Instance-Level Adaptation of Foundation Models for Forecasting with Covariates](https://mlsanity.com/paper/2509.13906/) (2025)
- [Real-world energy data of 200 feeders from low-voltage grids with metadata in Germany over two years](https://mlsanity.com/paper/2602.03521/) (2026)
- [FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting](https://mlsanity.com/paper/2604.22328/) (2026)
- [Multivariate Financial Forecasting using the Chronos Time Series Foundation Models](https://mlsanity.com/paper/2605.21504/) (2026)
- [Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics](https://mlsanity.com/paper/2607.01966/) (2026)
- [t0: A Time-Series Foundation Model for Forecasting with Context](https://mlsanity.com/paper/2609.24559/) (2026)
- [Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting](https://mlsanity.com/paper/2606.07457/) (2026)
- [Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence](https://mlsanity.com/paper/2607.02623/) (2026)
- [A Benchmark for Electrical Load Forecasting Across Grid Levels: Time-Series Transformers Outperform Established Methods](https://mlsanity.com/paper/2607.15705/) (2026)

## Abstract (arXiv)

Time series foundation models (TSFMs) increasingly offer covariate support, with calendar information being the most common type of categorical covariate in practice, as it is available for every point in time. However, how these features are encoded is largely treated as an implementation detail rather than as an object of study, despite encoding being one of the few design choices left for pretrained models at inference time. With the present study, we demonstrate that the way information is propagated into the model substantially affects forecast accuracy of TSFMs. Therefore, we systematically compare seven calendar encodings, including three conventional target-agnostic representations (ordinal, one-hot, and cyclic) and four target encodings, across four state-of-the-art TSFMs on nine datasets from multiple domains in a zero-shot rolling evaluation. The nine datasets are influenced by social activities, such as weekends and holidays, making calendar information particularly relevant for forecasting. We find that encoding choice affects forecast accuracy across all models, with MASE differences of up to 9.9 % on non-holidays and 83 % on holidays within a single model. Effectiveness and utilization vary substantially across models. Improvements are concentrated around holidays, where calendar information provides signals unavailable from target history, while some model encoding combinations also improve non-holiday forecasts. A SHAP-based attribution analysis locates the contribution of the covariates relative to the autoregressive component and explains why some model-encoding combinations degrade performance. Our findings suggest that current benchmarks for covariate-informed TSFMs can distort model comparisons by imposing fixed encoding strategies.