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.
Free will — free will and volition, as philosophy and as science — compatibilism and its rivals, manipulation and responsibility, and the neuroscience of voluntary action such as the readiness potential (group: philosophy; ADR-025).
12 of 547 CLAIM documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| CLAIM-047 | Possessing an action-generating regime is not the same as its being practically effective | The distinction the paper inherits from Frankfurt (THEORY-120) and generalizes beyond desires: the audit’s “established foundation”. | Active |
| CLAIM-062 | That every regulator with a higher-order attractor counts as having a will is acceptable once agency is kept apart from phenomenal experience | The owner’s reply at U34: minimal wills for simple systems are no reductio, and corporations can coherently act freely or have their hand forced. Superseded when the paper chose to suppose its agent instead. | Superseded — by CLAIM-080 |
| 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-354 v2 | Freedom of will and autonomy come in degrees along several dimensions, among them viable reachability, control cost, robustness to disturbance, governance reconfigurability, revisability and motivational integration, and agents compare by inclusion of what they can viably reach under matched conditions: a partial order with incomparable pairs, not a scalar, and a gradient only of a declared measure | The owner’s, U9 of the exchange of 2026-10-17: “controllability of a system isn’t binary, and neither is sensitivity to perturbation”, so can the account speak of “gradations (perhaps even gradients/spectra?) of freedom of will/autonomy”. Worked out by A9 §3 and §7, A10 §7 and A15’s central thesis. The dimensions vary separately, and comparison is by inclusion of viably reachable sets under matched conditions, a partial order, the shape CLAIM-128 has in the transport line. The sharp edge: it does not measure metaphysical free will or responsibility, and reachable-set size is not monotone with autonomy, since a precommitment can shrink the set while making an endorsed project realizable. | Proposed |
| CLAIM-532 | Self-formation, in the sense the record holds (the transformation dimension of a will-organization), is the production by an agent’s own activity on a discrepancy it cannot yet resolve of a maintained capacity, a new distinction it can make legible or a new channel by which it can act, that outlasts the discrepancy and serves a class of later ones; it is told apart from learning an action by transfer to discrepancies of the same class after the inducing conditions are gone, and from a capacity installed or upheld from outside by interventions on the processes that produce and maintain it | The positive account A33 §7 offered, at the owner’s U33 of the exchange “Assess SDT Coverage” (2026-11-02), sharpened by the reader of U32–U33 so that it can fail. The record held self-formation as a capacity (CLAIM-025, TERM-023) and what does not show it (CLAIM-540: an observer’s learning; CLAIM-522: recovery does not show provenance); it held no account of what self-formation produces. A33 wrote it; adopting it is the owner’s call. It is a non-libertarian reading of Kane’s self-forming actions (CLAIM-022’s note of 2026-11-02). The steps A33 chains, discrepancy to discrimination to response to maintained capacity to revised governance, are not a sequence (CLAIM-474). | Proposed |
| CLAIM-533 | The sensitivity that formal chaos gives a will’s dynamics is not control over them: in Kane’s self-forming actions, chaotic amplification keeps the outcome open, but it magnifies the agent’s efforts, uncontrolled fluctuations and outside inputs alike, so what would make the outcome the agent’s is how its own control couples to the amplifying directions, relative to noise and to other parties’ inputs and with what feedback, which sensitivity does not supply; and under weak noise what amplification touches lasts only where it reaches the slow modes | The owner’s, at U16 and U20 of the exchange “Assess SDT Coverage” (2026-11-02). U16: “I think there’s an intuitive control theoretic connection here through the lens of controllability and sensitivity to change and chaos and slow modes.” U20: “this brings us back to controllability vs sensitivity, and why I was alluding to a connection between Kane’s freedom and (formal) chaos.” The owner first said it at U9 of 2026-10-17 (“controllability of a system isn’t binary, and neither is sensitivity to perturbation”); the controllability half was filed as CLAIM-354 and CLAIM-345, and the sensitivity half had no code. This is its second appearance. Its demonstrated part is CLAIM-542. | 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-539 | Jennings’s attention as the source of a free will has Frankfurt’s two-level architecture with its upper level changed from an attitude to a process: the whole collection of an agent’s interests, prioritizing, settles which first-order interest becomes effective, as a second-order volition does for Frankfurt, but by metacontrol and not by endorsement; so it inherits unchanged the objection that a manipulated organization can meet the condition, and what it adds to Frankfurt is that the process forms new interests and is a contextually emergent cause | The owner’s U14 of the exchange “Assess SDT Coverage” (2026-11-02): “would it be fair to say Jennings theory is Frankfurt with a hat on?” Answered from CLAIM-122’s note of 2026-10-18, which separates higher-order volition, an attitude about what should be effective, from metacontrol, the machinery that alters what becomes effective. First filed as a note on CLAIM-122, since the paper was unread. The owner then supplied it, and the reading (NOTE-1508) bears the claim out: attention is prioritization by a collection of interests, with no endorsement anywhere, and no historical condition. | Proposed |
| 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 | A13 of the exchange “Assess SDT Coverage” (2026-11-02), answering the owner’s U13, what the Dirichlet–categorical reading implies for Jennings’s attention as the source of a free will. A13: “Self-formation requires a causal update, not merely a posterior update in the observer.” Correct, short and not held. It limits the record’s own H1/H2 reading (CLAIM-536) and A11’s suggestion that LDA already has “a primitive analogue of a will-organization”. Rechecked here by simulation. | Active |
| CLAIM-542 | Sensitivity does not fix the allocation or the authorship of control: linearized, every input reaches the final state through the same transition operator, ∂x_T/∂w_t = Φ(T, t)B_w(t), so systems with the same Lyapunov spectrum can differ arbitrarily in what an agent’s own channel, an outside party’s channel and noise each reach and at what least energy; and along one unstable direction a larger exponent λ lowers the least effort to reach a displacement, since W_T = b²(e^{2λT} − 1)/2λ grows with λ, while a constant open-loop input against white noise entering the same direction has terminal signal-to-noise ratio tending to (bu/σ)√(2/λ), which falls as λ grows, so only feedback that observes the state turns cheaper control into reliable direction | The demonstrated part of the owner’s U16 and U20 of the exchange “Assess SDT Coverage” (2026-11-02), “controllability vs sensitivity”. A20 §2 stated the impulse case (“the relative contribution is not determined by e^{λT}”) and A22 §5 the channel case. The scalar signal-to-noise result is the reader’s derivation, checked by simulation. It sharpens the owner’s point: sensitivity makes control cheaper and, without feedback, less decisive against noise. CLAIM-345 holds the cost formula and not the allocation across channels. | Active |
| CLAIM-544 | If a willed agent is the jurisdiction of its will-organization, then governing one’s own governability is in part governing one’s own individuation, in the constitutive sense of individuation at that level: a revision of the will-organization that changes which regimes it governs changes which willed agent there is, so a self-forming revision can be a re-individuation and not only a change in an agent’s states, and whether the revised jurisdiction continues the earlier agent is a question of continuation, not of resemblance | The join the owner’s U31 of the exchange “Assess SDT Coverage” (2026-11-02) asked for, “connect to individuation”, made through the owner’s own entry for it, CLAIM-170, which A31 never cited. A positive account, filed under U33. The reader of U30–U31 drafted it; adopting it is the owner’s call. It names its sense of individuation, as TERM-088 asks and A31 did not: the constitutive sense, relative to CLAIM-170’s level and target. CLAIM-284 is its nearest held neighbour, a self as an organization that takes part in governing its own transformation. | Proposed |
| CLAIM-545 | Freedom of will, in the operational sense, is an agent’s governance of its own governability: the extent to which its own organization makes the relevant distinctions legible, gives the demands they raise practical efficacy, directs its transitions, and revises the relations that govern those three, including under another’s interference; openness, sensitivity and controllability of outcomes each fall short of it, and domination is another’s capacity to govern those same relations, used or not | A26 of the exchange “Assess SDT Coverage” (2026-11-02), written at the owner’s request for the synthesis “without all the hedging” (U26), after “synthesize” (U25). The owner asked for the strong form and did not state or endorse its wording; adopting it is the owner’s call. The phrase is A’s, from A22 §3 (“a will that governs its own governability”) through A24 to A26. Its parts are held, two of them the owner’s: CLAIM-354 and CLAIM-523, with CLAIM-485 and CLAIM-404. What it adds is the identification. The record had dimensions of freedom and no thesis of what freedom is. Three qualifications A26 dropped are restored: the sense is operational, the claim is descriptive, and it is open to the manipulation objection. | Proposed |