# Integrated information as a common signature of dynamical and information-processing complexity

arXiv: https://arxiv.org/abs/2106.10211 · HTML: https://mlsanity.com/paper/2106.10211/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2021.

## Built on by (most cited first, 5 of 5)

- [Emergent Coordination in Multi-Agent Language Models](https://mlsanity.com/paper/2510.05174/) (2025)
- [Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks](https://mlsanity.com/paper/2210.02996/) (2022)
- [A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning](https://mlsanity.com/paper/2601.06851/) (2026)
- [Early warning indicators via latent stochastic dynamical systems](https://mlsanity.com/paper/2309.03842/) (2023)
- [An AI Theory of Mind Will Enhance Our Collective Intelligence](https://mlsanity.com/paper/2411.09168/) (2024)

## Abstract (arXiv)

The apparent dichotomy between information-processing and dynamical approaches to complexity science forces researchers to choose between two diverging sets of tools and explanations, creating conflict and often hindering scientific progress. Nonetheless, given the shared theoretical goals between both approaches, it is reasonable to conjecture the existence of underlying common signatures that capture interesting behaviour in both dynamical and information-processing systems. Here we argue that a pragmatic use of Integrated Information Theory (IIT), originally conceived in theoretical neuroscience, can provide a potential unifying framework to study complexity in general multivariate systems. Furthermore, by leveraging metrics put forward by the integrated information decomposition (PhiID) framework, our results reveal that integrated information can effectively capture surprisingly heterogeneous signatures of complexity -- including metastability and criticality in networks of coupled oscillators as well as distributed computation and emergent stable particles in cellular automata -- without relying on idiosyncratic, ad-hoc criteria. These results show how an agnostic use of IIT can provide important steps towards bridging the gap between informational and dynamical approaches to complex systems.