Model techniques map
Techniques

specific method · not yet filed

no direct optimization pressure on chain-of-thought

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we decided not to put any direct optimization pressure on the CoT for either of our two open-weight models.

usedpost trainingin gpt-oss-120b and gpt-oss-20bOpenAI