arXiv AI June 16, 2026 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)

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 $p < 10^{-5}$.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

benchmarks

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

arXiv Machine Learning

6d ago

Orientation, not magnitude: the causal structure of task-vector interference in merged language models

arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.

By Chencheng Zhu

llms efficiency safety

arXiv AI

Jul 29

From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios

arXiv:2607. 25546v1 Announce Type: new Abstract: Given a model that is already trained, which features does it rely on causally versus spuriously?

By Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris

arXiv Machine Learning

Aug 3

Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?

arXiv:2607. 29484v1 Announce Type: cross Abstract: Interventional data is widely regarded as the gold standard for teaching models causal reasoning.

By Xining Xun

llms robotics

arXiv AI

Jul 29

Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners

arXiv:2607. 25532v1 Announce Type: new Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$).

By Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris

benchmarks

arXiv AI

Jun 9

Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures

arXiv:2606. 08275v1 Announce Type: cross Abstract: When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observability) or whether it passed (evaluation), but not which step caused the failure.

By Jaineet Shah

llms agents benchmarks

Related stories

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

Orientation, not magnitude: the causal structure of task-vector interference in merged language models

From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios

Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?

Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners

Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures