Remark. Label timing and non-anticipating feedback [ftip-0040]
✍️source

The index attached to a label does not determine when its information becomes available. The process-supervision construction in [lightman2023verify, Section 2.6] supplies step-indexed training labels, but it does not require every such label to be available while the response is being generated.

This distinction determines which interventions are admissible. An online agent may act on currently measurable feedback; an offline learner may use a post-hoc label for a past prefix; a causal claim needs assumptions connecting either signal to the consequences of the earlier action.

Remark. Label timing and non-anticipating feedback [ftip-0040]
✍️source

Reference. Let's verify step by step [lightman2023verify]

Outcome and process feedback [ftip-003V]

Definition. Outcome-supervised reward model [lightman2023verify, Section 2.5, ``Outcome-supervised reward models''] [ftip-003W]

Definition. Process-supervised reward model [lightman2023verify, Section 2.6, ``Process-supervised reward models''] [ftip-003X]

Remark. Terminal and intermediate supervision [lightman2023verify, Sections 2.5--2.6] [ftip-003Y]

Definition. Online measurable feedback [ftip-003Z]

Remark. Label timing and non-anticipating feedback [ftip-0040]
✍️source

Example. Terminal and process labels on the same four-step trace [ftip-0041]