# time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models

arXiv: https://arxiv.org/abs/2509.05801 · HTML: https://mlsanity.com/paper/2509.05801/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 6 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Toto: Time Series Optimized Transformer for Observability](https://mlsanity.com/paper/2407.07874/) (2024)
- [GluonTS: Probabilistic Time Series Models in Python](https://mlsanity.com/paper/1906.05264/) (2019)
- [Transformers in Time-series Analysis: A Tutorial](https://mlsanity.com/paper/2205.01138/) (2022)
- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [Exploring Representations and Interventions in Time Series Foundation Models](https://mlsanity.com/paper/2409.12915/) (2024)
- [Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting](https://mlsanity.com/paper/2412.08099/) (2024)
- [Time-Series Foundation AI Model for Value-at-Risk Forecasting](https://mlsanity.com/paper/2410.11773/) (2024)
- [DANLIP: Deep Autoregressive Networks for Locally Interpretable Probabilistic Forecasting](https://mlsanity.com/paper/2301.02332/) (2023)

## Built on by (most cited first, 4 of 4)

- [GITCO: Gated Inference-Time Context Optimization in TSFMs](https://mlsanity.com/paper/2606.05332/) (2026)
- [Formalizing and falsifying causal pathways of rare events](https://mlsanity.com/paper/2605.31254/) (2026)
- [Event Signature Transfer: Model-Agnostic Forecast Scenario Construction from Historical Events](https://mlsanity.com/paper/2609.23074/) (2026)
- [Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models](https://mlsanity.com/paper/2609.34316/) (2026)

## Abstract (arXiv)

While transformer-based foundation models excel at forecasting routine patterns, two questions remain: do they internalize semantic concepts such as market regimes, or merely fit curves? And can their internal representations be leveraged to simulate rare, high-stakes events such as market crashes? To investigate this, we introduce activation transplantation, a causal intervention that manipulates hidden states by imposing the statistical moments of one event (e.g., a historical crash) onto another (e.g., a calm period) during the forward pass. This procedure deterministically steers forecasts: injecting crash semantics induces downturn predictions, while injecting calm semantics suppresses crashes and restores stability. Beyond binary control, we find that models encode a graded notion of event severity, with the latent vector norm directly correlating with the magnitude of systemic shocks. Validated across two architecturally distinct TSFMs, Toto (decoder only) and Chronos (encoder-decoder), our results demonstrate that steerable, semantically grounded representations are a robust property of large time series transformers. Our findings provide evidence for a latent concept space that governs model predictions, shifting interpretability from post-hoc attribution to direct causal intervention, and enabling semantic "what-if" analysis for strategic stress-testing.