The paper proposes Iterated Amplification, a training strategy that builds a training signal for difficult problems by combining solutions to easier subproblems.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Supervising strong learners by amplifying weak experts → states its contribution → The paper proposes Iterated Amplification, a training strategy that builds a training signal for difficult problems by combining solutions to easier subproblems.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.