chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
Why it matters
Shows a concrete technique for probing which teacher model an open model was likely distillationTraining a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.Full definition → from, using reasoning-prefill overlap as a lineage signal.
