Definition. Verifiable reward [lambert2024tulu3, Section 6, equation (8), and the immediately following paragraph] [ftip-0049]

Given a deterministic correctness indicator \(v\) and reward scale \(\alpha >0\), the verifiable reward in the cited construction is

\[ R_{\mathrm {ver}}(x,y)= \begin {cases} \alpha ,&v(x,y)=1,\\ 0,&v(x,y)=0. \end {cases} \]

The paragraph after Equation (8) sets \(\alpha =10\). Another method may choose a different scale or combine several checked components, but that transformation is part of its reward design. A reward is verifiable relative to the implemented check, not relative to every property an independent evaluator may care about.