Just a reminder that even if the core work of the transcribing is done automatically now, being a media accessibility specialist who ensures the transcribing works and it is attached correctly, performs advocacy work for accessibility, and manages these systems, is a worthwhile job and will stay so for a long time.
What you’re describing is called a citation or reference tree and they are used to visualize complex set of references. Web of Science has a nice one, Scopus also has a tree view, I believe. Google Scholar has the information to make one, but doesn’t.