Example. Terminal and process labels on the same four-step trace [ftip-0041]
Example. Terminal and process labels on the same four-step trace [ftip-0041]
A four-step arithmetic trace can receive a correct terminal label while retaining an incorrect intermediate process label.
The final answer \(19\) is correct, so outcome supervision supplies \(f_{\rm out}=1\). The declared process labels are \((f_1,f_2,f_3,f_4)=(1,1,0,1)\) and expose the corrected arithmetic error at step three. The labels are attached to the displayed prefixes, which remain unchanged by those annotations.
The two supervision regimes follow the outcome- and process-supervised reward-model constructions in [lightman2023verify, the outcome- and process-supervised reward-model subsections]. The two observations are thereby separated. Noise-free labels and a general policy advantage for process supervision are not consequences of the finite trace.