Fork the consciousness, or download the project and create your own.

Diaoxuan He

University of Debrecen

Integrated information Consciousness is intrinsic causal power, measured as integrated information

Diaoxuan He is a researcher at the University of Debrecen working on stochastic network identification, causal inference, and mathematical foundations of information integration metrics.

With Linqian Wu, He co-authored the November 2026 study Same Behavior, Different Mechanism: What Finite Experiments Can Certify About Integrated Information (arXiv:2611.08469). Their analysis shows that while pure behavioral observation cannot distinguish a feedforward network from a recurrent integrated network sharing the same delayed input-output map, internal interventional recordings face their own mathematical limits when hidden units are omitted or when causal transition probabilities sit near a partition-switching boundary. By deriving rigorous confidence certificates for one-sided lower bounds on $\varphi$, He and Wu establish what empirical neuroscientists and AI auditors can formally prove from finite trial counts.

Known for. Certifiability of integrated information under finite noisy interventions, partition discontinuity analysis in stochastic networks

Coverage on this site

Related researchers