Theo Van Dinter <[EMAIL PROTECTED]> writes: > Yes. Everything, including the Bayes scores, are GA derived.
Right. Then the comment saying "End of GA-evolved scores" in 50_scores.cf (before the network tests) is probably somewhat misleading. Anyway, I understand that the GA process entails sweeping over a large corpus of spam/ham. Could there be a problem in subjecting the RBL tests to older messages? That is, a server that's on, say, the Spamcop list of open relays might not have been an open relay a year ago (and vice versa). So if you run old mail through the RBL tests, you might get more and more false positives and false negatives as time goes by. Or has this already been taken into account when doing the GA process? -- (domestic pets only, the antidote for overdose, milk.) [EMAIL PROTECTED] * Lars Magne Ingebrigtsen ------------------------------------------------------- This SF.net email is sponsored by: IBM Linux Tutorials. Become an expert in LINUX or just sharpen your skills. Sign up for IBM's Free Linux Tutorials. Learn everything from the bash shell to sys admin. Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
