________________________________
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]
Sent: Tuesday, March 16, 2004 3:32 AM
To: [EMAIL PROTECTED]
Subject: No Bayes in headers.
I think I read that if you do not find the word "bayes" in any
of your emails headers, then Bayes is not working?
Here's an example of part of one of my headers:
X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on
davmail.davenport-industries.com.au
X-Spam-Status: No, hits=-5.0 required=5.0
tests=CLICK_BELOW,Dav_DJs_01
autolearn=ham version=2.63
X-Spam-Level:
To me, the Bayes system seems to have classed this email as HAM-
so it's working, eh?
Regards,
Julian Milano
IT Manager
snip
Hi Julian,
Not quite true, if bayes does not find enough existing "tokens", you
will not get a "BAYES_XX" hit in the tests. But in general if Bayes is
working, sooner or later you should see some of those results in the
tests= section.
In the case of this message, bayes did not classify it as ham, but the
message did score low enough for the bayes auto-learn system to "learn"
it as ham. Possibly the next time a similar message comes along it will
actually get a low "BAYES_XX" test.
HTH,
matt
