Matt Cutts and team wrote at the Google Blog that they have minimized "the impact of many Googlebombs" by "improving our [Google's] analysis of the link structure of the web." They then go into the history of the Googlebomb and explain why they did it...
Danny Sullivan with Google Kills Bush's Miserable Failure Search & Other Google Bombs does an excellent job looking at all the angles of this announcement (yea, he is even on the road when he wrote this). So look over there, I am going to steal his before and after screen shot for a search on miserable failure.
One thing Danny did not discuss in much detail was the specifics of the algorithm change, an aspect that is on the top of the mind of most SEOs right now.
For that, we can take a look at Bill Bill Slawski's comment on Danny's post.
Compare that to what Anna Patterson wrote in the section on "Document Annotation for Improved Ranking" in the following document:
Instead of [BOMB otherwords], it tries to locate "related phrases" (some examples in the patent application). It also provides a means of weighing the strength of related phrases.
Of course, they could be doing something different, but this is the only document I know of from Google that discusses a means of stopping Google Bombing: This approach has the benefit of entirely preventing certain types of manipulations of web pages (a class of documents) in order to skew the results of a search. Search engines that use a ranking algorithm that relies on the number of links that point to a given document in order to rank that document can be "bombed" by artificially creating a large number of pages with a given anchor text which then point to a desired page. As a result, when a search query using the anchor text is entered, the desired page is typically returned, even if in fact this page has little or nothing to do with the anchor text. Importing the related bit vector from a target document URL1 into the phrase A related phrase bit vector for document URL0 eliminates the reliance of the search system on just the relationship of phrase A in URL0 pointing to URL1 as an indicator of significance or URL1 to the anchor text phrase.
Matt Cutts replied commending Bill on his find, but saying he cannot confirm or deny if this patent is used in the new link analysis.
Let me paraphrase the paraphrase from Bill's quote.
A related phrase bit vector for document URL0 eliminates the reliance of the search system on just the relationship of phrase A in URL0 pointing to URL1 as an indicator of significance or URL1 to the anchor text phrase.
Seems like a nice method, but who knows...