Deprecate ogbg-code and update to ogbg-code2
This version provides a major change in ogbg-code
.
ogbg-code
has been deprecated due to prediction target (i.e., method name) leakage in input AST.ogbg-code2
has been introduced that fixes the issue., where the method name and its recursive definition in AST are replaced with a special token_mask_
.
We sincerely thank Charles Sutton (@casutton) for finding the data leakage in our dataset.