# Causal interpretation rules for encoding and decoding models in neuroimaging

arXiv: https://arxiv.org/abs/1511.04780 · HTML: https://mlsanity.com/paper/1511.04780/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2015.

## Built on by (most cited first, 10 of 10)

- [Discovering Causal Relations and Equations from Data](https://mlsanity.com/paper/2305.13341/) (2023)
- [Same Cause; Different Effects in the Brain](https://mlsanity.com/paper/2202.10376/) (2022)
- [Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience](https://mlsanity.com/paper/2408.12664/) (2024)
- [Explainable AI needs formalization](https://mlsanity.com/paper/2409.14590/) (2024)
- [Feature salience - not task-informativeness - drives machine learning model explanations](https://mlsanity.com/paper/2602.09238/) (2026)
- [Minimizing False-Positive Attributions in Explanations of Non-Linear Models](https://mlsanity.com/paper/2505.11210/) (2025)
- [Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer](https://mlsanity.com/paper/2605.22488/) (2026)
- [Interpretability from a new lens: Integrating Stratification and Domain knowledge for Biomedical Applications](https://mlsanity.com/paper/2303.09322/) (2023)
- [A Lightweight Generative Model for Interpretable Subject-level Prediction](https://mlsanity.com/paper/2306.11107/) (2023)
- [cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context](https://mlsanity.com/paper/2602.20396/) (2026)

## Abstract (arXiv)

Causal terminology is often introduced in the interpretation of encoding and decoding models trained on neuroimaging data. In this article, we investigate which causal statements are warranted and which ones are not supported by empirical evidence. We argue that the distinction between encoding and decoding models is not sufficient for this purpose: relevant features in encoding and decoding models carry a different meaning in stimulus- and in response-based experimental paradigms. We show that only encoding models in the stimulus-based setting support unambiguous causal interpretations. By combining encoding and decoding models trained on the same data, however, we obtain insights into causal relations beyond those that are implied by each individual model type. We illustrate the empirical relevance of our theoretical findings on EEG data recorded during a visuo-motor learning task.