# kaal:claim:7456999-061

**Claim.** The record's measured advantage over passing visible checks changes sign under an arbitrary file-order tie-break, so the quantity is not resolved at this sample size.

**Type.** failure  **Support.** evidenced

**Holds when.**

- the comparison between highest-record and passes-the-checked-cases selectors

**Source quote.**

> That comparison is also unstable in a way the interval already implies. Selecting the first satisfying artifact in file order, an arbitrary choice, reverses the sign and the record loses by 0.0511. Averaging over which satisfying artifact is chosen, which is the honest treatment because file order carries no meaning, the record wins by 0.0374. A quantity that changes sign under a tie-break has not been measured at this sample size.

**From.** Wulf A. Kaal, *Reinforcement Learning from Reputation Feedback* (2026), V.A.4 What the cohort does not show, stated at the same volume, page 23

**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.** empirical-evidence, research-methods, ai-and-agents

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