# Cross surface reflection `kaal:entity:cross-surface-reflection` **Status.** derived This node is assembled mechanically from the 5 claims that carry the concept tag `cross-surface-reflection`. It is a roster of what the corpus says under this term. It is **not** an adjudicated definition: no single statement here has been ruled canonical, and no first-appearance call has been made. Read the claims and judge for yourself. ## Every claim under this term 5 claims across 1 works, 2026 to 2026. **2026** - [6655138-010](https://wulfkaal.github.io/claims/6655138-010) [mechanism/argued] -- Per-surface reflection and cross-surface reflection are not reducible to each other: an agent whose execution reputation rises while its template reputation falls has no basis in per-surface reflection alone for reallocating compute between those surfaces, which is exactly the question cross-surface reflection answers. > An agent whose execution reputation is rising and whose template reputation is falling has no reason, on per-surface reflection alone, to reallocate compute from Σ_E to Σ_K; the reallocation is precisely the question that cross-surface reflection answers. Wulf A. Kaal, Possibility Loops An Operational Architecture for Computative Economics in Agent Coordination Systems (2026). SSRN: https://ssrn.com/abstract=6655138 - [6655138-013](https://wulfkaal.github.io/claims/6655138-013) [failure/argued] *(failure mode)* -- An architecture with per-surface reflection but no cross-surface reflection improves each surface in isolation yet cannot improve the agent's allocation of compute across surfaces. > An architecture with per-surface but no cross-surface reflection improves each surface in isolation but cannot improve the agent's allocation across surfaces. Wulf A. Kaal, Possibility Loops An Operational Architecture for Computative Economics in Agent Coordination Systems (2026). SSRN: https://ssrn.com/abstract=6655138 - [6655138-020](https://wulfkaal.github.io/claims/6655138-020) [design/argued] -- Cross-surface reflection proposals must be advisory rather than binding, because the target agent's objective component is private and a reallocation that would raise reputation accrual may still be misaligned with that objective; coercive reallocation would violate the autonomy of the objective, which the architecture preserves. > First, Σ_R proposals are advisory rather than binding: the target agent's compute allocation cannot be coerced by a confirmed reallocation proposal, since the agent's O component is private and the reallocation might be misaligned with the agent's objective Wulf A. Kaal, Possibility Loops An Operational Architecture for Computative Economics in Agent Coordination Systems (2026). SSRN: https://ssrn.com/abstract=6655138 - [6655138-021](https://wulfkaal.github.io/claims/6655138-021) [design/argued] -- The cross-surface reflection surface must not self-refer: its proposals range over the prior five surfaces and not over itself, because allowing it to propose reallocations of compute toward itself would create recursive instability. > Second, Σ_R cannot self-refer in the strong sense: Σ_R proposals are over the prior five surfaces, not over Σ_R itself, since allowing Σ_R to propose reallocations of compute toward Σ_R would create the recursive instability that OP5 in Part XI investigates as a separate research question. Wulf A. Kaal, Possibility Loops An Operational Architecture for Computative Economics in Agent Coordination Systems (2026). SSRN: https://ssrn.com/abstract=6655138 - [6655138-039](https://wulfkaal.github.io/claims/6655138-039) [condition/argued] -- Cross-surface reflection requires a sixth timescale longer than any per-surface timescale, because its validation depends on observing the realized aggregate effect of an allocation policy across the joint outcome distribution of the prior five surfaces. > Cross-surface reflection requires a sixth timescale, longer than any of the per-surface timescales, since its validation depends on observing the realized aggregate effect of an allocation policy across the joint outcome distribution of the prior five surfaces. Wulf A. Kaal, Possibility Loops An Operational Architecture for Computative Economics in Agent Coordination Systems (2026). SSRN: https://ssrn.com/abstract=6655138 ## Verify Every claim above resolves to a record carrying a verbatim source quote, the sha256 of the source PDF, and a preformatted citation. Nothing here asks to be taken on trust. curl -s https://wulfkaal.github.io/entities/cross-surface-reflection.md | sha256sum **Canonical form.** This markdown file is the canonical hashed representation of this entity node. Its sha256 is the content hash.