# Which Histories Matter for Time Series Forecasting? Learning Predictive Relevance with Future Supervision

arXiv: https://arxiv.org/abs/2608.23221 · HTML: https://mlsanity.com/paper/2608.23221/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Retrieval Augmented Time Series Forecasting](https://mlsanity.com/paper/2411.08249/) (2024)
- [TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster](https://mlsanity.com/paper/2503.07649/) (2025)
- [Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift](https://mlsanity.com/paper/2410.09836/) (2024)
- [Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation](https://mlsanity.com/paper/2505.02138/) (2025)
- [Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting](https://mlsanity.com/paper/2412.08435/) (2024)
- [Improving Time Series Forecasting via Instance-aware Post-hoc Revision](https://mlsanity.com/paper/2505.23583/) (2025)
- [Predicting the Future by Retrieving the Past](https://mlsanity.com/paper/2511.05859/) (2025)
- [Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models](https://mlsanity.com/paper/2110.14993/) (2021)
- [Stationarity-Aware Retrieval-Augmented Time Series Forecasting](https://mlsanity.com/paper/2606.04135/) (2026)
- [Nearest Neighbor Multivariate Time Series Forecasting](https://mlsanity.com/paper/2505.11625/) (2025)
- [Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers](https://mlsanity.com/paper/2601.21641/) (2026)
- [Channel-wise Retrieval for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2604.05543/) (2026)
- [Semantics-Enhanced Retrieval-Augmented Time Series Forecasting](https://mlsanity.com/paper/2606.14941/) (2026)
- [Learning to Query History: Nonstationary Classification via Learned Retrieval](https://mlsanity.com/paper/2604.07027/) (2026)
- [KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncertainty](https://mlsanity.com/paper/2608.06748/) (2026)

## Abstract (arXiv)

Retrieval-augmented time-series forecasting typically selects historical examples by similarity between observed pasts, although similar pasts can evolve differently. We propose Predictive Relevance Retrieval (PRR), which uses realized future compatibility as privileged supervision to learn a retrieval function that remains strictly past-only at inference. PRR combines Pearson retrieval with a futuresupervised predictive representation to expand candidate support, then reranks the union using statistical and learned pair relations. Across six datasets and four long horizons, PRR improves Pearson retrieval in 23 of 24 conditions, reducing AnalogFutureMSE by 26.7% on average. A candidate-budget-matched variant, PRR-B100, retains nearly the same retrieval improvement while using at most 100 candidates at inference, showing that the gain is not explained simply by a larger candidate pool. We then connect the retriever to five frozen forecasting backbones using validation-calibrated trust. Downstream effects are heterogeneous, and calibration primarily reduces harmful retrieval use rather than making improved retrieval universally beneficial. These results show that predictive relevance and forecast utility are empirically distinct objectives.