# kaal:claim:7456999-033

**Claim.** The multiplicative-weights regret bound limits performance against the realized pool resolution, but does not show that the pool resolution is externally correct.

**Type.** failure  **Support.** argued

**Holds when.**

- the unkeyed reputation update in equation 3

**Source quote.**

> What the regret bound gives is that the weighted pool does not do much worse than the best fixed validator in hindsight, measured against the realized pool resolution. It does not give that the pool resolution is externally correct.

**From.** Wulf A. Kaal, *Reinforcement Learning from Reputation Feedback* (2026), III.A Validation Pool Architecture, page 12

**Cite as.** Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026). SSRN: https://ssrn.com/abstract=7456999

**Verify.** sha256 of source PDF `01016fbbcc25cad205cebd59ea686d8dfee8ae9b632095d86ba6c9a900456a4b` at https://raw.githubusercontent.com/wulfkaal/Academic-Papers/main/papers/pdf/Kaal%20-%202026%20-%20Reinforcement%20Learning%20from%20Reputation%20Feedback.pdf

**Topics.** ai-and-agents, reputation, research-methods

**Canonical form.** This markdown file is the canonical hashed representation of the claim. Its sha256 is the content hash used for attestation.