# CausalMamba: Scalable Conditional State Space Models for Neural Causal Inference

arXiv: https://arxiv.org/abs/2510.17318 · HTML: https://mlsanity.com/paper/2510.17318/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models](https://mlsanity.com/paper/1905.10857/) (2019)
- [Breaking Feedback Loops in Recommender Systems with Causal Inference](https://mlsanity.com/paper/2207.01616/) (2022)
- [Deep Recurrent Modelling of Granger Causality with Latent Confounding](https://mlsanity.com/paper/2202.11286/) (2022)

## Built on by (most cited first, 1 of 1)

- [Latent-Space Causal Discovery from Indirect Neuroimaging Observations](https://mlsanity.com/paper/2602.09034/) (2026)

## Abstract (arXiv)

We introduce CausalMamba, a scalable framework that addresses fundamental limitations in fMRI-based causal inference: the ill-posed nature of inferring neural causality from hemodynamically distorted BOLD signals and the computational intractability of existing methods like Dynamic Causal Modeling (DCM). Our approach decomposes this complex inverse problem into two tractable stages: BOLD deconvolution to recover latent neural activity, followed by causal graph inference using a novel Conditional Mamba architecture. On simulated data, CausalMamba achieves 37% higher accuracy than DCM. Critically, when applied to real task fMRI data, our method recovers well-established neural pathways with 88% fidelity, whereas conventional approaches fail to identify these canonical circuits in over 99% of subjects. Furthermore, our network analysis of working memory data reveals that the brain strategically shifts its primary causal hub-recruiting executive or salience networks depending on the stimulus-a sophisticated reconfiguration that remains undetected by traditional methods. This work provides neuroscientists with a practical tool for large-scale causal inference that captures both fundamental circuit motifs and flexible network dynamics underlying cognitive function.