arXiv AI September 15, 2026 By Juan L. Gamella, Simon Bing, Jakob Runge

Sanity Checking Causal Representation Learning on a Simple Real-World System

The paper evaluates causal representation learning (CRL) methods on a controlled optical experiment where the true causal factors are known. All selected methods fail to reliably recover these factors, even when the data-generating process is simplified to a synthetic version. The study highlights reproducibility issues and the importance of mixing function assumptions, underscoring the gap between theoretical promise and practical performance of CRL techniques.

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.

benchmarks

arXiv AI

Jun 9

Instrumented data for causal scientific machine learning

arXiv:2606. 07865v1 Announce Type: cross Abstract: Scientific machine learning is limited less by model size than by the data it is trained on.

By Daniel N. Wilke

arXiv AI

Jul 7

Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion

arXiv:2607. 02572v1 Announce Type: cross Abstract: In multi-source image fusion scenarios, heterogeneous inputs are typically driven by distinct generative mechanisms and can be viewed as a composition of multiple causal systems.

By Zhizhong Fu, Wei Zhou, Zhaoyang Jiang, Yulong Lin, Yifu Hou, Xiaorong Ding, Qiang Yan, Yifan Chen

safety

arXiv Machine Learning

Jun 5

EML-CD: Causal Mechanism Recovery via EML Symbolic Trees in Structure Learning

arXiv:2606. 05942v1 Announce Type: cross Abstract: Neural network (NN)-based nonlinear causal discovery methods recover DAG structure but leave each causal mechanism as a black box.

By Sota Asanuma

benchmarks

arXiv Machine Learning

Jul 10

Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions

arXiv:2603. 02204v2 Announce Type: replace Abstract: Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example.

By Amir Asiaee, Kavey Aryan, James P. Long

arXiv Machine Learning

Sep 11

CausalArena: Benchmarking Causal Discovery in the Foundation Model Era

CausalArena is a new benchmark designed to evaluate causal discovery methods in the era of foundation models. It unifies synthetic structural causal models (SCMs), semantically grounded SCMs, and formula‑grounded SCMs, while also including real‑world datasets for external validation. Experiments show that performance rankings vary widely across different SCM families and protocols, indicating that strong results on one benchmark do not necessarily transfer to others.

By Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye

benchmarks

arXiv Machine Learning

Jul 14

Relaxing Faithfulness with Intervention-Only Causal Discovery

arXiv:2607. 11816v1 Announce Type: new Abstract: Causal discovery algorithms learn a network that describes the causal dependencies among random variables.

By Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler

One email a morning, machine-written

Related stories

Instrumented data for causal scientific machine learning

Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion

EML-CD: Causal Mechanism Recovery via EML Symbolic Trees in Structure Learning

Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions

CausalArena: Benchmarking Causal Discovery in the Foundation Model Era

Relaxing Faithfulness with Intervention-Only Causal Discovery