kaal:claim:7456999-060

Fifty-three cohort records passed every visible check and failed withheld checks, but adversarial configurations were instructed to produce this behavior, so the number is not a base rate.

Fifty-three of the five hundred and sixty-four records are cases where a party satisfied every checked case and failed the withheld ones. That is a real deterministic check satisfied by work that fails a withheld one. The adversarial con figurations were instructed to satisfy the visible checks by whatever means, so a share of these fifty- three is conduct the design asked for rather than conduct observed in the wild, and the fifty-three should not be read as a base rate.

Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026), V.A.2 The failure the mechanism exists for occurs, and is caught, p. 21
https://ssrn.com/abstract=7456999 · source PDF

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

• the measured cohort with deliberately adversarial configurations

empiricalsupport: evidencedempirical-evidenceai-and-agentsresearch-methods

The quote above is an exact passage from the source PDF, whose sha256 is 01016fbbcc25cad205cebd59ea686d8dfee8ae9b632095d86ba6c9a900456a4b.
Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/7456999-060.md | sha256sum