Given the discussion of the recent problem with the Habeas mark being autolearned as ham, I think it would be a good rule of thumb to skip the bayes autolearning when a message has ANY negative score. This will prevent future abuses of these types of scores from polluting the database.
The merits of auto-learning it as spam is also debatable. What if the bayes_90 score was set so it balances the habeas and other third part "not spam" headers and let the other rules decide? Best Regards, Bob ------------------------------------------------------- This SF.net email is sponsored by: Perforce Software. Perforce is the Fast Software Configuration Management System offering advanced branching capabilities and atomic changes on 50+ platforms. Free Eval! http://www.perforce.com/perforce/loadprog.html _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
