Model techniques map
Techniquespost-trainingreward modelling

specific method · filed under post-training

Binary task verifier

Assigns a binary task reward using task-specific checks such as unit tests, assertion harnesses, or exact-answer matching.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

For SWE-style tasks this is the repository’s own unit-test suite run against the agent’s patch; for terminal tasks it is the task’s bash-side assertion harness; for tool-integrated math problems it is exact numeric-answer match against the gold solution.

corepost trainingin Laguna XS.2Poolside

Filed alongside

Other methods under post-training :: reward modelling.