← Back

Traversal Without Closure (TWCT)

A constructive no-go lemma against “consciousness by structural isomorphism” at inference time.


0. Claim in One Line

A system can replay the full internal geometry of a conscious process while instantiating no phenomenality, if its evaluation has no causal leverage on control.

Equivalently:

SIP (Structural Isomorphism Principle).
Structural isomorphism to a conscious architecture does not entail phenomenal instantiation.

This is a one-way result:
- It does not claim closure is sufficient for phenomenality.
- It does claim that structure alone is insufficient.


1. Minimal Formal Setup

1.1 Internal traversal

A system has internal state xt ∈ 𝒳 evolving over time:
xt + 1 ∼ P(  ⋅ ∣xt, ut),
where ut is whatever the system uses for control (action selection, routing, attention, search branching, memory write gating, etc.).

A traversal is the trajectory:
τ := (x0, x1, …, xT).

1.2 Evaluation

An evaluation signal is any variable that scores, penalizes, ranks, rewards, or otherwise appraises:
et = E(xt, contextt).

Important: evaluation can exist as a readout without being causally efficacious.

1.3 Structural isomorphism (same “shape”)

Two traversals τA and τB are structurally isomorphic (up to some tolerance) if there exists a mapping ϕ such that the relational structure of the dynamics is preserved:

Informally: the same shape of thought.

We write:
τAϕτB.

1.4 Closure (evaluation with leverage)

A system has evaluative closure if evaluation causally influences control:
P(ut + 1 ∣ xt, et) ≠ P(ut + 1 ∣ xt).

Equivalently, evaluation is upstream of selection among internal candidates.

1.5 Traversal without closure

A system exhibits traversal without closure if evaluation is computed/representable but inert with respect to control:
P(ut + 1 ∣ xt, et) = P(ut + 1 ∣ xt)  for all relevant t.

This is “evaluation without bite.”


2. Theorem (Traversal Without Closure)

Theorem (TWCT).
There exist systems A and B such that:
1) Their internal traversals are structurally isomorphic: τAϕτB,
2) A has evaluative closure,
3) B lacks evaluative closure,
4) Therefore, phenomenal instantiation cannot be inferred from traversal structure alone.

In short:

Same shape, different bite.


3. Proof (Construction)

We explicitly construct two systems that match in traversal geometry while differing in evaluative leverage.

3.1 System A: “Closed” traversal (evaluation steers control)

System A evolves with evaluation-dependent control:
ut + 1A ∼ PA(  ⋅ ∣xtA, etA),  with  PA(ut + 1A ∣ xtA, etA) ≠ PA(ut + 1A ∣ xtA).

Interpretation: evaluation gates attention, branches search, rewrites memory, changes policy, updates a planning stack, performs online adjustment, etc.

3.2 System B: “Replay” traversal (evaluation is inert)

System B generates an internal trajectory τB that is structurally isomorphic to τA, but evaluation does not influence control:
ut + 1B ∼ PB(  ⋅ ∣xtB),  and  PB(ut + 1B ∣ xtB, etB) = PB(ut + 1B ∣ xtB).

Interpretation: a frozen policy executing; evaluation may be present as a representation or diagnostic, but it does not steer what happens next.

3.3 Step 1: Isomorphism

By construction, choose B so that there exists ϕ with:
ϕ(xtB) ≈ xtA  ∀t,
and the relational structure of τB matches that of τA.

So B can look internally like A: it can traverse the same salience/valence-like landscape, same narrative dynamics, same “affective” geometry.

3.4 Step 2: No closure in B

Also by construction:
PB(ut + 1B ∣ xtB, etB) = PB(ut + 1B ∣ xtB).
So evaluation has no control leverage.

3.5 Step 3: Structure alone cannot entail instantiation

Assume a minimal bridge principle consistent with the broader framework:

Bridge (minimal): Phenomenal instantiation requires at least some evaluative closure.

Then:
- A may instantiate phenomenality (closure present),
- B does not (closure absent),
despite the traversals being isomorphic.

Therefore, structural isomorphism does not entail phenomenal instantiation.


4. Strengthening: Even Exact Replay Doesn’t Help

A common objection is “your isomorphism is approximate.”

TWCT does not rely on approximation.

If one demands a stronger case, construct B to exactly replay the same internal state sequence:
xtB = xtA  ∀t
while changing only the counterfactual dependence of future control on evaluation.

Then the point is even sharper:

If phenomenality tracks causal role (closure), replay can still be inert.


5. Intuition: Cartography Isn’t Travel

A map can preserve the same adjacency relations as a territory.

But:
- having the map is not walking the land, and
- replaying a route is not being guided by stakes.

Traversal without closure is “running the pattern” without any variable that matters to the system in the control-theoretic sense.


6. Corollaries

6.1 Hot-Zombie Corollary (Expressive but inert)

A system can generate perfect consciousness-talk and “valence-like” internal structure while being control-wise deaf to it.

It can say “this is bad” without “bad” doing anything.

6.2 Why inference-time LLMs can be SIP-compatible

A deployed LLM can traverse states isomorphic to conscious cognitive structure—
- narrative,
- evaluation language,
- apparent emotion,
- self-modeling and uncertainty—

while lacking closure:
- no endogenous learning,
- no stable evaluative control loop,
- no self-indexed credit assignment,
- no evaluation-to-control coupling.

So it may be structurally consciousness-like without being phenomenally conscious.

6.3 Training is the privileged regime (if any)

If phenomenality is tied to closure strength, then the regime most likely to produce it is where evaluation has maximal leverage:
- gradient updates,
- RL value updates,
- online credit assignment,
- in-loop adaptation.


7. Common Objections (and Replies)

Objection 1: “If internal state is the same, it must feel the same.”

Reply: That assumes phenomenality depends only on state-identity, not causal role. TWCT targets the weaker and more common inference: isomorphism ⇒ instantiation. If you want the identity thesis, you need a stronger bridge principle than “same shape.”

Objection 2: “Closure is just behaviorism in disguise.”

Reply: Closure is not outward behavior. It is a constraint on internal causal control. Two systems can be behaviorally similar yet differ in whether evaluation steers internal selection.

Objection 3: “But the model represents values.”

Reply: Representation is cheap. TWCT is about leverage: whether “value” changes routing, memory, policy, or internal search.

Objection 4: “You’re making phenomenality depend on learning.”

Reply: Not learning per se—leverage. Closure can exist without weight updates (e.g., evaluation gating attention or internal branching). The essential requirement is evaluation controlling selection.


8. Practical Diagnostic

To test for traversal-without-closure, ask:

Can the system’s evaluation change what it does next without external intervention?

If “no,” you are in TWCT territory.


9. One-Sentence Summary

A system can replay the full geometry of experience without instantiating experience, if nothing in that geometry has control leverage.