---
identifier: iit:claim/unfolding-argument
title: The unfolding argument
vetted_by: "William G. P. Mayner"
formalism: iit-4.0-2026
summary: >-
  The claim that IIT is either falsified or unscientific because any recurrent
  network can be unfolded into a behaviourally identical feedforward network,
  and IIT assigns the two different Φ.
claim:
  - text: >-
      Here, using theorems from the theory of computation, we show that causal
      structure theories are either false or outside the realm of science.
    source: >-
      Doerig, Schurger, Hess & Herzog (2019), "The unfolding argument: Why IIT
      and other causal structure theories cannot explain consciousness",
      Consciousness and Cognition 72:49–59, abstract.
      doi:10.1016/j.concog.2019.04.002
restatement: >-
  Any recurrent network can be replaced ("unfolded") by a feedforward network
  with the same input–output function. IIT assigns the two different values —
  the feedforward twin necessarily has φ_s = 0 — while their behaviour is
  identical, so no behavioural experiment can distinguish them. If evidence
  about consciousness must be behavioural (the argument's premise), IIT is
  either contradicted by that evidence or untestable by it.
status: disagreement
response: >-
  IIT rejects the premise, not the construction. The premise — that
  input–output behaviour is the only admissible evidence about consciousness —
  is functionalism taken as an epistemic axiom, and IIT does not grant it:
  the theory starts from the existence of experience (the axioms) and
  identifies an experience with the cause–effect structure specified by a
  substrate, so two substrates with the same input–output function but
  different causal structure differ in Φ. That the unfolded feedforward twin
  has φ_s = 0 and is not conscious is a prediction of the theory, not a
  refutation of it, and it is testable against non-behavioural evidence
  (perturbation and lesion studies among others). Both parties understand
  each other and differ on the premise of what counts as evidence, hence the
  status. The published reply is iit:ref/tsuchiya-2020; the dispute is also
  catalogued in iit:ref/albantakis-nd.
computation: iit:result/feedforward-3node
see_also:
  - iit:measure/phi-s
sources:
  - ref: iit:ref/oizumi-2014
    at: 'Conscious complexes and unconscious "zombie" systems can be functionally equivalent; Fig. 21'
  - ref: iit:ref/tononi-2025b
    at: "The 'unfolding' argument"
  - ref: iit:ref/albantakis-2014
    at: 'Discussion, "When does evolution favor integrated structures?"'
  - ref: iit:ref/albantakis-2021c
  - ref: iit:ref/tsuchiya-2020
  - ref: iit:ref/albantakis-nd
---

The unfolding construction itself is not in dispute, and it did not originate
with Doerig et al.: IIT published it five years earlier. IIT 3.0 has a section
titled "Conscious complexes and unconscious 'zombie' systems can be
functionally equivalent" (iit:ref/oizumi-2014, Fig. 21). It cites the
universal approximation theorems for feedforward networks (Cybenko 1989;
Hornik et al. 1989), unfolds a recurrent system over time into a feedforward
network with the same input–output behaviour, and shows that the recurrent
system forms a complex with Φ > 0 in every state while the feedforward one
forms no complex at all. Albantakis et al. (iit:ref/albantakis-2014,
Discussion) make the same point the same year: "any task could, in principle,
be solved by a modular brain with Φ = 0 given an arbitrary number of elements
and time-steps". Albantakis's commentary "Unfolding the Substitution Argument"
(in the corpus document `consciousnessrealist`) notes both precedents: "Guess
who introduced this issue?" IIT used the construction to argue that functional
equivalence does not entail phenomenal equivalence; the unfolding argument
invokes the same proof against the theory (iit:ref/tononi-2025b, "The
'unfolding' argument"; iit:ref/albantakis-2021c makes the same point with the
Krohn–Rhodes theorem). What the
theory denies is that behavioural equivalence settles the question of
experience — on IIT's account the physical substrate's cause–effect structure,
not the function it computes, is what an experience is. The linked computation
shows the feedforward half of the dissociation concretely: a three-unit
feedforward chain has φ_s = 0 because it is not strongly connected, so a
partition cutting in the (absent) feedback direction makes no difference.