My question, should bayes ignore the habeas headers by default?
Perhaps not by default, but right now it's probably a good idea.
In general, any sudden shift of behavior from something commonly seen only in nonspam to commonly seen in both causes trouble for bayes. The current SWE situation is only a problem because it is scored based on the history of SWE.
If I started a fresh new bayes database today and trained it with only fresh email, the SWE headers would be learned as a neutral token.
------------------------------------------------------- The SF.Net email is sponsored by EclipseCon 2004 Premiere Conference on Open Tools Development and Integration See the breadth of Eclipse activity. February 3-5 in Anaheim, CA. http://www.eclipsecon.org/osdn _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
