Glossary · Use and training pipelines
Process supervision
Supervision applied to intermediate procedure or steps rather than only the final outcome; outcome supervision derives its signal from terminal outcomes alone. A training use of a process-resolution signal, not a mechanism.
Defined in
Handbook · InstrumentSignals and resolutionVerdict, score, preference or critique; about a step, action, artifact, trajectory or population. Why PRMs, value models and margins are different objects.Related terms
- Process evaluation
- Judges intermediate steps, actions, states, or evidence acquisition. Justified when the path itself matters; harmful when it forces one canonical chain.
- Process reward model (PRM)
- A learned judge operating at step or state resolution. "Process" names the resolution, not a rung above outcome checkers.