Topics — What a work is about. Nucleation holds whatever reading the owner files here, whether or not an Anthology of the SOTA topic could also hold it; instruction for ML practice belongs to the anthology (ADR-048). The words are seeded from the clusters the reading-time triage of 2026-09-25 found, and grow by decision.
Behavioral integration — how an organism’s many control systems come to act as one — action selection and competition between systems (habitual and goal-directed, automatic and willed), hierarchical and feedback control, intertemporal conflict and self-control, and evidence accumulation to a decision. One of four unities kept apart (ADR-024).
17 of 547 CLAIM documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| CLAIM-156 v3 | Mindfulness integrates a population of interests by changing which of them may act, and not only by changing what they value: noticing an impulse as an impulse suspends the step from its momentary dominance to its control of action, and that step needs no change in the discount curves | The record’s own conjecture, made in answer to the owner’s prompt of 2026-10-11. It places mindfulness among CLAIM-027’s conditions of efficacy (suspension, accessibility), so it is a second individual-scale instance of that thesis. The one direct study read as summarised (LIT-906) points the other way, and the claim says so. It does not say mindfulness never changes valuation. | Proposed |
| CLAIM-158 | Systems differ in whether “who drives?” has an answer at a given level of description, and the kinds form a spectrum: fully top-down, bidirectional, emergent from the whole, and between | The owner’s thesis of 2026-10-11: “it’s probably worth differentiating between systems where ‘who drives?’ has an answer wrt a particularly level of description or not. I think there’s is probably a spectrum/gradient/distribution of kinds here.” The record grounds it in the information decomposition (LIT-025), whose downward-causation and causal-decoupling terms separate the kinds, and in proportional causation (THEORY-133), which makes a higher level the cause system by system. | Proposed |
| CLAIM-159 v3 | The record’s rival accounts of will are claims about drive profiles in different cells: Ainslie’s interests are aggregate or emergent, the expected value of control is top-down, and will-organization is the maintained organization that governs how the drive profile changes | The assistant’s reading, offered in chat on 2026-10-11 and filed at the owner’s prompt. Ainslie’s will has no governor: the person is “just the resultant” of bargaining interests, which is aggregate, or emergent if resolve is a property only the recursion has. The expected value of control posits a dedicated specifying system, which is top-down. The will paper’s will-organization is the maintained organization of relations that decides which regime is effective, so it governs the drive profile’s changes over time. That is the owner’s point that “who drives” is not constant. | Active |
| CLAIM-162 v3 | In flow an activity’s immediate reward and its longer-run value coincide, so no interest has to be overridden (synchronization as non-crossing valuations, with no dynamical mechanism claimed), and that is why focused action in flow is reported as effortless | The record’s own conjecture, made in answer to the owner’s prompt of 2026-10-11. It is grounded only weakly: the effort-cost account is a reading, and the flow literature is registered unread. It says that in flow there is nothing for will to do. It does not say flow is the best or the normal way to act as one. | Proposed |
| CLAIM-163 v2 | ”Synchronization” is an analogy without a mechanism: phase synchrony among coupled oscillators has a coupling, an order parameter and transitions, valuations that fail to cross have none of these, and the word adds nothing to “the curves do not cross” | The record’s own anticipated objection to the owner’s framing, and the kind ADR-032 found most often real: same structure, not the same mechanism. Open. TERM-050 defines synchronization without dynamics, so the claims survive with the word replaced, but then the word is only a name. The body says what would turn the analogy into a mechanism. | Superseded — by ARG-016 |
| CLAIM-169 v2 | On Ainslie’s account the population of interests is produced by desynchronized valuation, not given by a fixed architecture: an agent is many interests over a choice only as far as its valuations of that choice cross within the choice’s horizon | The record’s reading of THEORY-067, made in answer to the owner’s prompt of 2026-10-11. Interests are individuated by the delay at which each dominates, so where curves do not cross there is nothing to individuate them. The self’s intertemporal multiplicity is then a variable, not a constant. It does not say that all multiplicity of self is intertemporal. | Proposed |
| CLAIM-198 | Preference reversal is not yet disunity: interests that govern a choice at disjoint times glue, and a self is divided over a choice only on an overlap, which the agent’s prediction of its own later valuation creates | Take an agent’s interests as sections over contexts of choice, each governing the windows of time in which its valuation ranks first. If the windows do not overlap, the sections glue (CLAIM-197): someone who prefers the diet in the morning and the cake at night is a time-indexed preference, not a divided self. Division needs an overlap, a choice on which both interests bear at once. On Ainslie’s account that overlap is made by recursive self-prediction: the present choice is valued as a forecast of the later ones, so the later interest’s valuation enters the present context. That is where intertemporal bargaining happens, and it is the coupling CLAIM-163 found missing. | Proposed |
| CLAIM-261 v2 | Synchronization of an agent’s interests is desirable, but not necessary for acting as one: internal conflict shows a human agent acting while its interests stay divided | The owner’s answer to QUESTION-078. A human agent who acts against a standing temptation acts as one agent while its interests stay divided, so synchronization is not what acting as one consists in. Synchronization is still better when it is available: nothing has to be overridden, and CLAIM-162 says that is why flow is effortless. | Active |
| CLAIM-262 v2 | Whether an agent’s regimes are coordinated by discrete switches or by continuous reorganization depends on how the agent is constituted; both occur | The owner’s answer to QUESTION-079: both forms are possible, and which one an agent shows depends on its constitution. An agent made of a population whose choices accumulate like a drift-diffusion process reorganizes continuously. Twitch Plays Pokémon approximates one, best in democracy mode with the tally visible as votes arrive. The consequence for CLAIM-163’s transition test is that it must be stated per constitution. A missing switch counts against coordination only in an agent built to switch. | Proposed |
| CLAIM-286 v2 | Habit, akrasia, rumination, rigidity and insight can be modelled as regimes of one organization, in which processes transform shared meaning and allocate one another’s influence, with trust, specialization and higher-level agency arising from its history and not imposed | A7’s central thesis, the explanatory half of the manuscript, kept apart from the constitutive half (CLAIM-284) as A7 itself asked. Its novelty is the unification, not any ingredient: “multi-agent cognition, competing control systems, temporal discounting, self-exciting processes, and organizational emergence all have substantial literatures”. It is the claim CLAIM-278 objects to. It does not say these processes are a self. | Proposed |
| CLAIM-344 v3 | Resolve is a maintained organization of precedence, commitment and revision that keeps a temporally extended policy effective across changes in locally dominant evaluations while keeping the capacity to revise it; mere slowness or persistence is not resolve | The owner’s frame, U37 of the exchange of 2026-10-17: “I think emergence of “resolve” could be an interesting frame within which to examine our will-organization framework.” A37 defined it, and A39 to A47 revised it each turn: retention and revision as separate grades, fragility against rigidity (A41), access against authority (A42), and governance that makes its own repeated exercise unnecessary (A45, A47). The record already holds a theory of resolve, Ainslie’s recursive staking of future choices (THEORY-067); this is its organizational and revisable form, placed in CLAIM-159’s will-organization cell. The sharp edge: the standard for when revision is warranted is not supplied, and is QUESTION-087’s open problem. | Active |
| CLAIM-358 v3 | Learned local accommodation can reduce the amortized cost of recurrent arbitration: where a recurring conflict among an agent’s processes admits a stable accommodation, settling it among the processes can cost less over repeated encounters than escalating each instance to a higher-level process that mediates or overrides, though local negotiation and the relations it needs are not free | The owner’s, U45 of the exchange of 2026-10-17: “processes which can navigate disagreement amongst themselves require fewer resources from the system than processes which need to activate additional subsystems to resolve disagreement.” A45 put it in conditional form: where a recurring conflict admits a stable local accommodation, learning it amortizes the cost of higher-order mediation. It refines CLAIM-261’s “pays for its unity in effort”: the divided agent pays for escalation. The title stated the owner’s thesis unconditionally until the owner’s review of the filing put it in A45’s conditional form: local negotiation, and keeping up the relations among specialists it needs, have costs of their own. The sharp edge: it does not say local settlement is always cheaper, that an integrated agent works less hard, or anything about authenticity. | Proposed |
| CLAIM-362 | Non-domination of an agent’s subcomponents is a candidate constituent of authenticity as an organizational achievement, not a sufficient criterion of ownership: higher-level processes need not impose the outcome because the lower-level ones already support it or settle their disagreement among themselves, and a process that rarely decides keeps access to the roles in which it is consequential | The owner’s, U45 of the exchange of 2026-10-17: “‘authenticity’ should be treated as an organizational achievement characterized by non-domination of subcomponents”. A45 granted it as “an important correction to our developing theory”, against A44’s “An authentically maintained goal may demand more effort, not less”. A46 refined non-domination to “continued access to consequential roles”. A candidate constituent of authenticity and a candidate repair of CLAIM-016’s “integrated”, not an operational test of ownership: the title said “Authenticity is …” until the owner’s review of the filing narrowed it. The authenticity line was set aside on 2026-10-05; filing this does not reopen it, and whether it reopens is the owner’s call. The manipulation objection stands (CLAIM-364). | Proposed |
| CLAIM-364 v4 | Processes conditioned never to object coordinate without override at the same behaviour and supervisory cost as processes that negotiate, so the two part only under intervention, when a constituent dissents, or in their history | A45’s, U45 of the exchange of 2026-10-17, against the owner’s non-domination criterion (CLAIM-362) read through its economy: “a system whose subordinate processes have been conditioned never to object might exhibit perfect local harmony”, and “A quiet subordinate process isn’t necessarily a satisfied one.” It is the manipulation objection (THEORY-1118), and QUESTION-071, applied to the new criterion. It does not say the criterion fails, only that cost cannot certify it. The authenticity line was set aside on 2026-10-05; whether it reopens is the owner’s call. | Proposed |
| CLAIM-435 v2 | Veit’s common currency and ALARM’s override are two regimes of one ordering serving as the negotiation’s potential, compensatory and overriding, so their rivalry over what the first felt valence did becomes the question whether the earliest potential orderings are continuous: in motivational trade-off experiments, a continuous indifference curve between a noxious cost and a resource for Veit, a discontinuity at a threshold beyond which no resource buys the cost for ALARM; only a graded override, deciding at every level of its own intensity, lacks a currency altogether | A consequence of the owner’s reframing of valence as ordering-potential (CLAIM-440). THEORY-101 records that its rivalry with ALARM “would dissolve if ALARM’s “100% weight” were recast as a weight in a common currency rather than an override of it.” It is recast instead: both are an ordering serving as the negotiation’s potential, compensatory or overriding, and the trade-off test separates them by continuity. Corrected on reading Debreu before filing: a threshold override still has a (discontinuous) currency; only a graded override has none (CLAIM-436, part 3a). | Proposed |
| CLAIM-534 | A plural will’s motivational integration, a dimension of freedom of will the record names and leaves unanalysed, is the extent to which the demands it maintains are jointly met, within tolerances it can recognize, across the contexts where they interact, and kept so under its own dynamics; it is neither agreement among the demands nor the dominance of one, and its parts come apart: realizability (the tolerance frontier), realization (governance frustration), maintenance (viability) and the allocation of the tolerance each demand gives up | A positive account, filed at the owner’s U33 of the exchange “Assess SDT Coverage” (2026-11-02): “are there any positive accounts or even just hypotheses we should consider documenting on the record (even if just as proposals)?” It joins the owner’s U27, “compatibility of tolerance bounds”, to CLAIM-354’s “motivational integration”, which the record names and does not analyse. The wording is A29’s, sharpened by the reader of U27–U29; adopting it is the owner’s call. Proposed: the identification is argued, and its formal half is CLAIM-538. | Proposed |
| CLAIM-538 | On a finite graph of contexts whose overlaps carry preferred real offsets a and tolerances δ_e ≥ 0, an assignment within every tolerance, |Dx − a| ≤ δ, exists exactly when no cycle’s holonomy exceeds the sum of its tolerances; with every δ_e > 0 the least uniform enlargement of the tolerances that admits one is the largest ratio, over simple cycles, of holonomy to summed tolerance, so the obstruction is certified by a cycle; the feasible allocations of tolerance depend on the offsets only through their class in H¹, so local adjustment can move a mismatch among the overlaps of a cycle and never remove it; and an evaluation that omits one overlap of every witnessing cycle reports a compatibility that does not hold | The owner’s U27 of the exchange “Assess SDT Coverage” (2026-11-02), “compatibility of tolerance bounds”, with U28’s pointer to the record’s sheaf tools, worked out at A28 §3 and A29 §§3–4, 7 and A32’s Claim A. The feasibility criterion is the classical feasible-differential theorem of network flows (Rockafellar 1984; no checked identifier, not registered), and the ratio is LP duality, so the result is granted, not the record’s discovery. What the record adds is the reading: the frontier is an invariant of the obstruction class, governance chooses where on it the mismatch falls, and omission can fake compatibility. Checked by linear programming against brute-force cycle enumeration on random graphs. | Active |