random_2azkXJ
The oxbridge (as in "the bridge of the ox", a very logical outcome from "the ford of the ox" and "the bridge of the cam") are more of commercial enterprises than teaching institutions, and the preference for them are first and foremost the result of commercial advertising. The business model in here is to attract a great mass of pupils, be very selective about it (in order to have high-profile prospects), be very expensive (because the networking happening there must worth the hassle), then selling the achievements of these high-potenial strictly-preselected material to others as the results of its own merit. The research, the eccentric curriculum, or any other quirk that sets these institutions apart from others are just secondary. That is the naked truth.
From a simple test, this tool is at the hobby level. The text is not interpreted semantically, because the so-called summarization is nothing but blocks of text from the original text, copied ad-literam. It lacks any kind of rewording. My guess is that for content retrieval it employs the the most rudimentary model one can think of [1], does a plain token indexation, then chooses the blocks with the highest density of non-ordinary words.