The Oracle's documentation on bugs is paywalled... What is actually an improvement over others like Microsoft, that denies a bug with all their might, up to the point it is fixed, and then say the minimum possible.

Anyway the most recent pair I found on the wild was a problem that made indexes of georeferenced data fail at random, pushing your queries into a non-indexed search and breaking things like materialized views, and one that causes some inconsistency on testing clobs for null or empty string (what made them impossible to test for either when it applies). But there's a well known one that breaks optimization plans at random and goes with the last try (it doesn't matter if that it will scan that table 100000 rows 1000 times), and there's some bug where if you create some tables, populate them, drop them and repeat enough times you will lose your database. But that's just from the top of my head.

Oh, of course, that isn't including designed behaviors like the one that takes your database offline if you don't do backups often enough (where "often enough" is something that you can estimate but never be sure about its frequency).