Consciousness as Uncommon Self-Knowledge: A Synergistic Information Framework
arXiv Preprint Archive May 11, 2026 via arXiv
Summary
AI-generated from the abstractA proposed criterion for consciousness, uncommon self-knowledge (USK), is the synergistic information a system carries about itself that exists only in the joint of its subsystems and is destroyed by decomposition. Drawing on information theory, the framework distinguishes consciousness (synergistic self-knowledge) from metacognition (redundant self-knowledge) and claims to resolve counterexamples to Integrated Information Theory, Global Workspace Theory, and Higher-Order Thought theories. It yields empirical predictions, including a timing dissociation in Global Workspace Theory where consciousness correlates with pre-broadcast synergy formation, and a dissociation between self-report and task-performance disruption under middle-layer perturbation in large language models. The proposal is consistent with findings that anaesthesia and Alzheimer's disease reduce synergistic information processing while preserving or increasing redundancy.
Study at a glance
Abstract
We propose uncommon self-knowledge (USK) as a candidate criterion for consciousness: synergistic information a system carries about itself that exists only in the joint of its subsystems and is destroyed by decomposition. Drawing on Gottwald's partition-lattice grounding of Partial Information Decomposition (PID), where redundancy corresponds to Aumann's common knowledge and synergy to the gap between separate and joint observation, we propose the synergistic component of self-directed information as a candidate formal signature for conscious processing. If correct, the framework would (1) offer a clean separation between consciousness and metacognition (synergistic vs. redundant self-knowledge), (2) provide principled resolutions to counterexamples that challenge IIT, GWT, and HOT, (3) be operationalizable via Partial Information Rate Decomposition (PIRD) with self-targeting, and (4) generate distinctive empirical predictions, the strongest being a GWT timing dissociation (consciousness correlates with pre-broadcast synergy formation, not broadcast itself) and a specific dissociation between self-report disruption and task-performance disruption under middle-layer perturbation in LLMs. The proposal is consistent with recent empirical findings that both anaesthesia and Alzheimer's disease specifically reduce synergistic information processing while preserving or increasing redundancy.