nucleation

CLAIM-414: Matched ordinary trajectories can conceal differences in an interpretation's efficacy, in the allocation of that efficacy, and in the maintenance of its enabling constraints: in two finite constructions, systems that agree under ordinary operation differ in each, and a specified intervention exposes the difference that passive observation of the matched trajectories does not

6 min read

Properties14
StatusActive
Version4
Rolethesis
Warrantdemonstrated
Tagsmathematics, individuation, consciousness
Lineevidence-for-experience, formal-apparatus
GroundsCASE-126 — Represented, authorized, self-authorized and self-maintained: three one-bit systems that agree while the interpretation is 0 and part under an intervention that sets it to 1, and two two-constraint systems with the same constant trajectory, one closed and one reset from outside, that part under one perturbation
SupportsCLAIM-427 — Evidence for the organizational-perspective framework comes in three grades: that different organizations produce the same ordinary behaviour, that they respond differently to independently specified interventions, and that a model representing the coupling of significance, authority and reproduction predicts those responses better than the strongest existing alternatives at matched complexity; only the third bears on the framework's defeater, and no grade counts if success is defined in the framework's own terms, CLAIM-454 — A latent feature or mode recovered from an organization's members' activity is at most a constituent of an organizational perspective, not the perspective: a feature allocation says which members take part in which modes, and whether those modes are organized into one perspective depends on the relations of access, uptake and authority among their carriers, which the same allocation leaves open
ComplementsCLAIM-407 — A coarse-graining exactly informationally closed under a process's ordinary dynamics need not preserve its responses to an intervention on the mechanism: for a declared intervention distribution ρ, independent of the state, the deficiency Γ = I(S; Y^(I) | T(S), I) can be positive, as in the hidden governance bit, where it is ρ(h = 1) bits; and Γ = 0 exactly when, for every intervention ρ charges, the response kernels are constant on T's fibres over the states of positive probability, CLAIM-194 — A gap or coupling criterion cannot tell a boundary a system produces from one imposed on it: a membrane the cell makes and a beam joining two pendulums pass alike, so the block test cannot by itself supply the individuality minimal agency needs
UsesTERM-070 — organizational closure, as closure of constraints: a set of constraints each of which depends directly on another in the set and has another depending on it (Montévil and Mossio 2015), distinct from informational closure and from a flame's maintenance of the conditions of its own combustion, TERM-073 — interpretation, as a context-dependent determination of significance: a transformation that differentiates information and establishes or revises its consequences within an operative organization, defined without experience
Illustrated byCASE-126 — Represented, authorized, self-authorized and self-maintained: three one-bit systems that agree while the interpretation is 0 and part under an intervention that sets it to 1, and two two-constraint systems with the same constant trajectory, one closed and one reset from outside, that part under one perturbation, CASE-161 — Reciprocally produced, externally reset and feedback-only governing rules in a 32-member population: with ordinary trajectories identical, reciprocal production repairs the loss of one rule and not of both and fails after producer outages of 36 updates for audit and 40 for admission, after an audit-rule pulse the next audit integrity is 1.00, 0.18 and 0.00 in the three arrangements, and a self-dependent production graph does not regenerate a zeroed rule, CASE-163 — Identifying how governing rules are maintained from diagnostic probes: a predictor fitted under reciprocal production fails under self-dependent production with histories matched, an audit pulse with a short producer interruption identifies which of four known mechanisms applies and predicts withheld interventions, and fitting decay and threshold as well helps after the parameters shift and hurts at nominal ones, within a known catalog and with every probe run on a counterfactual reset
Cited as “complements” byCLAIM-456 — Maintaining a governing rule internally, by the organization's own reciprocal production, can be more fragile than having it reset from outside: arrangements identical in ordinary operation can differ in which losses are repairable, and the self-produced rule can be lost to a double loss or an interruption of the work that produces it which outside reset survives, CLAIM-515 — Whether an organization has a cognitive property is four questions, not one: what information about the property can be recovered from its behaviour, what capabilities it can actually exercise, what mechanisms realize them, and whether it can maintain or transform those mechanisms; the four can come apart, and none should be silently substituted for another, CLAIM-521 — An organization's present coupling strength need not reveal the stability of the process maintaining it: in a constructed system whose maintained connector and capacities set a three-unit coupling, the recovery rate of the maintenance goes to zero at its saddle-node while the coupling's spectral gap there stays near 0.989, CLAIM-522 — Recovery under interventions on state cannot show where maintenance is realized: an outside controller that measures the constraint capacities and supplies the internal production law as state feedback yields the same trajectory under every perturbation of state, damage and recovery included, even with every capacity observed exactly; only interventions on the production mechanisms, relative to a declared boundary, separate the two, CLAIM-528 — That a mechanism realizes a capacity can mean that the capacity is produced through it over time or that the capacity consists in it at a time, and interventions show only the first: a pathway whose disabling changes the capacity after a delay is a cause, can be intervened on surgically, and can be located relative to a declared boundary, whereas every intervention on a capacity that consists in its parts also changes some part along another path, so that relation is underdetermined by intervention data and is inferred by abduction or from simultaneity and settled parthood; and which of the two a given dependence is depends on the time resolution at which a description treats the parts' response as instantaneous, CLAIM-530 — Where maintenance is realized is a question of constitutive relevance only through its parthood condition: an internal producer and an outside controller supplying the same production law as state feedback meet mutual manipulability's two manipulability conditions identically, since disabling or stimulating either changes the maintained capacities and intervening on the capacities changes the activity of either, so what puts one inside and the other outside is parthood, a boundary the experiments presuppose and do not find
Cited as “illustrates” byCASE-186 — A proposed study: an organization in a world whose hidden regime reverses and then leaves its hypothesis family, with evidence generation, admission and scoring separately lesionable, its diagnostic machinery maintained by its own reciprocal production, from outside, or not at all, and finite fuel shared among operation, maintenance and diagnosis, to find whether a second correction after injury to the diagnostic and copying machinery separates arrangements that correct the first failure alike
Cited as “rests on” byARG-025 — Matched ordinary behaviour and differing responses to intervention show that organizational perspectives explain what the record explained by self, CLAIM-519 — Competent behaviour does not establish an internal world model: over a fixed interface and a finite horizon, an agent with no model, whose actions are looked up from the history so far, reproduces the interaction distribution of an agent that has one exactly; a policy can identify predictive structure without any particular internal component realizing it, so compression and generalization support comparing candidate architectures, and establishing an internal mechanism needs evidence that discriminates candidate implementations, such as targeted interventions, CLAIM-540 — The persistence a Dirichlet–categorical hierarchy gives a run of selections is an observer's learning about a fixed mixture, not a change in what selects: under a uniform prior an observed first choice raises the predicted chance of repeating it from 1/2 to 2/3, while the same choice forced leaves it at 1/2, so the hierarchy's reinforcement is not evidence of self-formation or of a maintained will-organization, which need the mixture itself to change under the choice, CLAIM-543 — What separates a language model's distribution over personas from a distribution over organizational perspectives is not whether the latent model is hierarchical, since a mixture or an LDA-style admixture already is, but whether some latent components condition which others are available or consequential: a model whose components are exchangeable given their weights is organizationally flat however many levels its prior has, and dependencies among components count as organization (organization as relational arrangement) only where interventions, not fit, support them

Graph View

The claim

A10 proposed “four progressively stronger properties”: representation, efficacy, endogenous allocation and constitutive maintenance. “These are not four degrees of consciousness. They are different organizational facts, each requiring different evidence.” It built two constructions to show that they come apart. “Interpretation” here is TERM-073’s, and maintenance is closure of constraints in TERM-070’s sense. Both constructions are CASE-126, re-run here by script. Its tables are reproduced exactly.

  1. Efficacy and allocation. Systems R (Y = 0), X (Y = J) and E (Y = A·J, A’ = J, A₀ = 0) give Y = 0, 0 when J = 0. Under do(J₀ = J₁ = 1) they give 0, 0; 1, 1; and 0, 1. “Ordinary behavioral equivalence does not determine whether an interpretation is causally effective, nor whether its efficacy is allocated endogenously.”
  2. Maintenance. In the closed system each constraint takes part in producing the other, C₁ on even steps from C₂ and C₂ every step from C₁. The second system is reset to (1, 1) from outside. Both stay at (1, 1). After C₂ is set to 0 at t = 0, the first goes (0, 1), then (0, 0) for good, and the second returns to (1, 1). “The causal organization of maintenance can differ even when the maintained states and ordinary behavior are identical.”

The second system pair is the smallest closure CLAIM-395 allows: two constraints, one slow dependence (C₁ is conserved for two steps and made from C₂, which acts for one) and one fast. A10 did not cite CLAIM-395, but its construction meets that claim’s conditions (A) and (B).

Where it sits in the record

  • CLAIM-407 shows that a description exactly closed under ordinary dynamics can lose a system’s response to an intervention on its mechanism, as in the hidden governance bit (CASE-125). Part 1 is the same lesson for an interpretation’s authority, and part 2 for its maintenance.
  • CLAIM-194 holds that a gap or coupling criterion cannot tell a boundary a system produces from one imposed on it. Part 2 shows that a perturbation can tell produced maintenance from imposed maintenance where the ordinary trajectory cannot. It complements CLAIM-194 and does not answer it in general. CLAIM-194 is about boundaries read from observational statistics, and part 2 needs the intervention.
  • TERM-067’s governance-response profile is the tool for describing part
    1. A9 kept TERM-067’s own warning, that a response profile “would not automatically be a judgment about self-governance”.

What it does not say

  • Not that the four properties are logically independent pairwise or in general. Two constructions exhibit specific separations: efficacy and allocation in construction 1, maintenance in construction 2. They are existence results for those cases, not an independence theorem.

  • Not that only an intervention can tell the systems apart. Knowing their mechanisms tells them apart at once. The point is that the matched passive observations do not, and that a specified intervention does.

  • Not that any of the four facts is a mark of experience, or of a perspective. A10: “It does not establish agency, perspectival unity, or consciousness.” A11 then denied that maintenance (part 2) is necessary for a perspective at all (TERM-072).

  • Not that Boolean update rules are constraints in Montévil and Mossio’s sense. A10: “Boolean transition equations by themselves do not demonstrate that a biological or organizational system possesses genuine constraint-producing mechanisms.” The production relation is stipulated.

  • Not that the four are ordered by implication. A10: “These arrows indicate increasingly demanding explanatory claims, not logical implications.” Maintenance without rich representation is possible.

Note of 2026-10-22: an empirical parallel, and two criteria

  • A parallel in a trained model. In Gurnee et al. (NOTE-1069) the language of a passage is represented in all four tasks but is effective in only two, and only an activation swap tells them apart. That is the claim’s first separation, efficacy against representation, found in a real system and not constructed. It is an intervention result, not passive observation.
  • Criteria that behaviour cannot settle. Whyte et al.’s criterion of consciousness (THEORY-883) is a capacity to affect choice, and Laukkonen et al.’s “epistemic depth” (THEORY-882) is precision allocated from within. By this claim, matched behaviour can hide both, so behavioural tests for them, as Laukkonen et al. propose for AI, need an intervention.
  • Bo et al. (NOTE-1061) show where an appraisal is represented and where it changes affect, but by correlational imaging. It is a loose parallel, not an instance.

Note of 2026-10-26: the maintenance separation in a population

CASE-161 carries the claim’s second construction to a stochastic population of 32 members (dmarx/PerspectiveLab@7e2edc2): external reset, reciprocal production by two producer teams, and feedback only, with ordinary trajectories required by test to be identical. Loss of one rule, loss of both and producer outages separate them, and after the same audit pulse the next audit integrity is 1.00, 0.18 and 0.00. The production law differs from CASE-126’s. There one perturbation runs the closed pair into (0, 0). Here reciprocal production repairs a single loss in 48 of 48 runs and fails only on double loss or a long producer outage. The claim’s point holds under both laws.

CASE-163 bears on the claim’s second limit, that knowing the mechanisms tells the systems apart. Within a catalog of four known mechanisms, an audit pulse with a short producer interruption identifies which one applies in every reference run and predicts interventions never probed (dmarx/PerspectiveLab@9f82bfd). Decay and threshold are recovered only approximately. Both are stipulated constructions, not an independence theorem. The claim is unchanged.

Note of 2026-11-01: the separating intervention in the mechanism literature

  • The intervention is the mechanists’ “lesion”. The claim’s second construction separates the pair by a perturbation of the maintained constraints. The record’s later cases (CASE-161, CASE-163) separate theirs by knocking out production pathways. In Craver and Bechtel’s terms (LIT-1928, pp. 553–554) these are interlevel experiments, and in Bechtel and Abrahamsen’s (LIT-1936, p. 326) they are C3: clamp a part and see whether the phenomenon survives (THEORY-1289). Both readings agree with the claim’s second limit, that knowing the mechanisms tells the systems apart. Both also say such experiments show componency only relative to a boundary drawn beforehand (THEORY-1287, CLAIM-530).
  • A biological parallel to construction 2. Bechtel and Abrahamsen report the open question whether peripheral clocks keep their own rhythm or are damped oscillators reset by the SCN, and a model in which the two respond differently to a phase shift (p. 328; THEORY-1292). Same structure, not shown same mechanism: there the perturbation separates them because the two arrangements obey different equations.

No status, title or warrant changes.

Backlinks