If they're using something like GPT-3 on the backend, which they probably are, it probably can't provide any explanations or context (unless the output is memorized training data, like this); the output can be somewhat novel code not from any particular source, and while it might be possible to find relevant information on similar code, this would be a hard problem too.

EDIT: they appear to be interested in making it look for similar code, see here: https://docs.github.com/en/github/copilot/research-recitatio...