paper-with-me

Papers

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

2025-09-06 · Debdeep Sanyal, Aaryan Nagpal, Dhruv Kumar, Murari Mandal, Saurabh Deshpande 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.

📄 PDF Abstract BibTeX arXiv:2509.05801

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Inference Time Causal Probing in LLMs

2026-05-08 · Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Matthias Grossglauser arxiv

Causal probing methods aim to test and control how internal representations influence the behavior of generative models. In causal probing, an intervention modifies hidden states so that a property takes on a different v…

Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time

2026-04-28 · Jennifer Wendland, Nicolas Freitag, Maik Kschischo arxiv

Causal inference in continuous-time sequential decision problems is challenged by hidden confounders. We show that, in latent state-space models with time-varying interventions, observability of the latent dynamics from …

Causal Inference

Abstracting Causal Models

2018-12-10 · Sander Beckers, Joseph Y. Halpern

We consider a sequence of successively more restrictive definitions of abstraction for causal models, starting with a notion introduced by Rubenstein et al. (2017) called exact transformation that applies to probabilisti…

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

2026-07-09 · Amir Asiaee arxiv

Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one. These experimen…

Time Series Causal Link Estimation under Hidden Confounding using Knockoff Interventions

2022-09-23 · Violeta Teodora Trifunov, Maha Shadaydeh, Joachim Denzler

Latent variables often mask cause-effect relationships in observational data which provokes spurious links that may be misinterpreted as causal. This problem sparks great interest in the fields such as climate science an…

Time SeriesTime Series Analysis