arXiv:2610.08118v1 Announce Type: new Abstract: Covariate-aware time-series foundation models (TSFMs) promise training-free what-if answers for instrumented plants: the change in output that a differ...
arXiv:2607. 27263v1 Announce Type: new Abstract: Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation under-served exactly where it matters most, such as in healthcare, policy evaluation, and climate science.
arXiv:2607. 29484v1 Announce Type: cross Abstract: Interventional data is widely regarded as the gold standard for teaching models causal reasoning.
arXiv:2610. 12232v1 Announce Type: new Abstract: Test-time adaptation (TTA) methods for time-series forecasting update a deployed model, or a small adapter around it, from incoming ground truth.
The paper introduces a Causal Market Simulator using a continuous‑time causal prior‑data fitted network (PFN) to estimate market impact, addressing bias from informational flow that traditional models overlook. On a synthetic market prior with adjustable confounding, the PFN matches an unbiased oracle while a naive estimator overestimates by up to 68%. In zero‑shot tests on real limit‑order books and equity data, the model’s intervention responses align with ground‑truth scales and improve correlation with measured impact when a recurrent state‑space variant is used.
The paper introduces the concept of intervention fidelity in latent world models, measuring whether a model’s open‑loop transitions align with actual environment interventions. Experiments on TD‑MPC2, Cheetah, and DreamerV3 show that high reward fit does not guarantee fidelity, and that self‑supervised models can outperform task‑anchored ones in preserving intervention effects. The authors propose a capture‑gated audit to localize failures and argue that fidelity must be directly audited on the model’s native interface.
arXiv:2605. 09169v2 Announce Type: replace-cross Abstract: A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout $S = |W_{out} W_{in}|$, with early experiments suggesting the phenomenon generalized across architectures and benefited from interventional data at $p < 10^{-5}$.
arXiv:2503. 20546v2 Announce Type: replace-cross Abstract: We consider the problem of estimating the expected causal effect $E[Y|do(X)]$ for a target variable $Y$ when treatment $X$ is set by intervention, focusing on continuous random variables.
arXiv:2607. 19383v1 Announce Type: cross Abstract: Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series zero-shot.
arXiv:2610.02252v1 Announce Type: cross Abstract: Many scientific questions require reasoning about what was never observed: What if the conditions, interventions, or history had been different? Mode...
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
ACTIVA is a transformer‑based conditional variational autoencoder designed to estimate full interventional distributions from observational data without requiring interventional data, a causal graph, or per‑task fitting. It learns a conditional latent prior that amortizes causal knowledge across diverse training tasks, enabling a single forward pass to handle new causal models drawn from the training distribution. Empirical results on synthetic and biologically realistic gene‑expression simulations show that ACTIVA outperforms correlational baselines, reduces spurious non‑descendant effects, and matches strong amortized baselines, while also validating its theoretical mixture‑of‑distributions property on observationally equivalent models.