There was never a serious claim DOS copied CP/M code. The controversy was mostly about legality of reimplementation of the API, plus some pretty vague claims about copying the design: https://substack.com/@nemanjatrifunovic/note/p-178321556
I don't believe it, I think Kildall was lying. Enough source code is available to directly inspect this, even if Kildall's code was heavily obfuscated and supposedly translated to 8086 for 86-DOS