AI Insight
This paper proposes a mathematical framework called canonical functionalism, which refines computational functionalism about consciousness by grounding functional organization in a system's intrinsic state-transition structure rather than in observer-imposed interpretations or semantic labels. The canonical functional structure is defined as the minimal state-transition system obtained by grouping states with identical future behavioral profiles across all possible continuations, making the framework independent of external descriptions. Rather than claiming to identify which systems are conscious, the paper repositions functionalism by specifying the formal object over which theories of consciousness should be built, and reframes classic objections such as lookup tables and simulations as questions about structural preservation rather than outright refutations.
Why it matters
This framework offers a more rigorous and observer-independent foundation for functionalist theories of mind, which has implications for philosophy of mind, cognitive science, and debates surrounding machine consciousness and artificial intelligence. By formalizing what counts as genuine functional organization, it provides clearer criteria for evaluating whether computational systems could, in principle, instantiate consciousness-relevant structures.
arXiv:2605.21506v1 Announce Type: new
Abstract: Computational functionalism about consciousness is often criticized for relying on observer-relative interpretations of physical systems. This paper proposes a mathematical refinement of functionalism that avoids this problem. The central idea is that consciousness-relevant functional organization should be identified not with arbitrary input-output mappings, semantic labels, or externally imposed computational descriptions, but with a system’s canonical functional structure: the minimal state-transition structure obtained by identifying internal states that have identical future behavior under all possible continuations.
On this view, a state is functionally defined by its complete counterfactual role: how the system would evolve and respond from that state under possible future interactions. We call this position canonical functionalism. The framework does not claim to identify which systems are conscious, nor to show that functional organization is sufficient for consciousness. Rather, it identifies the canonical object over which functionalist theories of consciousness should be formulated: the task is to specify consciousness-relevant invariants, measures, or structural conditions over canonical functional structures, rather than over arbitrary semantic interpretations or superficial behavioral profiles. This reframes familiar objections about lookup tables, simulations, unfolding, and observer-relative computation: such cases do not by themselves refute functionalism, but force the functionalist to specify whether the relevant canonical structure is preserved, and if not, which additional structural features are missing.
Source: Canonical Functionalism: Defining Functional Structure without Observer-Relative Semantic Maps