Can they do it with corporate code where there are naming and style standards in abundance, and code reviews to ensure those guidelines are followed?
Presumably, yes. Style guides are 95% formatting, and if one RTFA (I know, I know), they look only at the structure of the parsed AST, not variable names, comments and whitespace. From the article:
Accuracy rates weren’t statistically different when using an off-the-shelf C++ code obfuscators. Since these tools generally work by refactoring names and removing spaces and comments, the syntactic feature set wasn’t changed so author identification at similar rates was still possible.
Since they look at code structure, they've even found identifying patterns that survive compilation and end up in the binary.
This is one of the coolest data mining results I've seen in quite a while.