kaal:claim:7456999-051

The paper withdrew its earlier Cramer-Rao efficiency conjecture because revisions could not make it coherent and comparable with deployed RLHF, and it makes no mean squared error claim.

Earlier versions stated a Conjecture 1 on Cramer-Rao ef ficiency dominance of the RLRF reward estimator over the RLHF reward estimator. It is withdrawn in Version 14. Successive revisions could not make it both internally coherent and a comparison with deployed RLHF. The paper makes no mean squared error claim.

Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026), IV.A The Withdrawn Efficiency Conjecture, p. 17
https://ssrn.com/abstract=7456999 · source PDF

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

• the withdrawn Conjecture 1

failuresupport: assertedresearch-methodsai-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/7456999-051.md | sha256sum