# kaal:claim:7456999-029

**Claim.** Format D combines reasoning supervision with adversarial argument, and its claimed increment is selecting revisions by which arguments moved a staked assessor, an increment no experiment in the paper tests.

**Type.** design  **Support.** argued

**Holds when.**

- the proposed Debate-Informed Revision format

**Source quote.**

> Format D sits between these two: like process supervision it trains on reasoning, and like debate it obtains that reasoning adversarially. Its only distinguishing feature is that the reasoning it keeps is the reasoning that moved an assessor who had a stake at risk. That selection rule is the contribution, and no experiment in this paper tests whether it helps.

**From.** Wulf A. Kaal, *Reinforcement Learning from Reputation Feedback* (2026), II.D The Nearest Literatures, and What Is Left Over, page 10

**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.