← Back to all news
arXiv AI By Ankit Hemant Lade, Sai Krishna Jasti, Indar Kumar, Aman Chadha

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

Read the original on arXiv AI →

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 $p < 10^{-5}$.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 31

DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series

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.

By Dennis Thumm, Billy Tim Anthony, Ying Chen
benchmarks
More like this →
arXiv Machine Learning
Sep 4

Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery

The paper investigates why differentiable causal discovery methods that encode expert priors as forbidden-edge constraints via an Augmented Lagrangian (ALM) penalty—termed the "guide, not bind" approach—often fail. It identifies two key failures: (1) the sequential penalty‑ramping ALM suppresses a true edge before counterfactual checks can detect it, and the proposed adaptive relaxation rule DADU violates necessary conditions for safe relaxation, leading to a high failure rate across thousands of training runs; (2) the standard correlation‑matching objective inherently ties a true edge and its reverse to the same cost, whereas covariance matching can separate them by a provable margin. The authors provide theoretical propositions, corollaries, and empirical evidence to support these claims.

By Sairam Sundararaman, Sara Girdhar, Manit Narasimha Murthy, Samrudh N, Bhaskarjyoti Das
More like this →