kaal:claim:7456999-062

The sweep's 67.7 percent annotator baseline is a simulated output rather than a published agreement rate or a measurement of human annotators.

In the sweep, the modeled RLHF baseline settles at 67.7% accuracy and RLRF exceeds 0.97, both under parameters the sweep sets. Neither figure is a published agreement rate, and Part V.B.1 explains why calling 67.7 the Ouyang-Coste bound conflates an output of the model with an input to it.

Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026), IX. Conclusion, p. 31
https://ssrn.com/abstract=7456999 · source PDF

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

• Finding 1 of the parameter sweep

failuresupport: assertedresearch-methodsempirical-evidenceai-and-agents

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/7456999-062.md | sha256sum