Remark. A decision and reproducible evidence are distinct [ftip-0048]
Remark. A decision and reproducible evidence are distinct [ftip-0048]
The same correctness decision can arise from different parsers, tests, proof kernels, or failure modes. Tülu 3 uses a scaled two-valued reward \(\alpha \) or \(0\), with \(\alpha =10\), in [lambert2024tulu3, Section 6, equation (8), and the immediately following paragraph]; it does not identify that reward with a complete record of the checking procedure.
Evidence enables later audits of false positives, false negatives, version changes, and shortcut exploitation. Reproducibility of the check still does not establish that the checked predicate equals the intended capability.