[SAtalk] anomy and..spamd?

2003-03-30 Thread Jonathan Nichols
Hey guys - Over the weekend I set up a "mailgate" box, following the directions I found at http://www.advosys.ca/papers/printable/postfix-filtering.html and so far, everything is working ok. I'd like to know if there's a way to get the "filter.sh" script they call for to use spamd instead o

[SAtalk] Spamassassin & Razor

2003-03-30 Thread Rafael Osuna
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hello all, I am new using Kmail&Spamassassin&Razor and I have two very basical questions: 1- When I run "razor-admin -register" or "razor-admin -crrate" I get the following error: "nextserver: discover0: No Razor Discovery servers available at this t

[SAtalk] false Return-Path: flagged whitelist

2003-03-30 Thread alan premselaar
Ok, so i'm running SA 2.50 (no bayes yet) site-wide as a gateway to my exchange server at the office here and it looks like a spam i received triggered my whitelist by adding: Return-Path: [EMAIL PROTECTED] to the headers. I want to have users in my domain on the whitel

Re: [SAtalk] Bayes accuracy and nspam/nham

2003-03-30 Thread Theo Van Dinter
On Sun, Mar 30, 2003 at 10:16:00AM -0800, Bart Schaefer wrote: > Theo remarked in another thread that Bayes is most accurate when the DB > nspam is approximately equal to nham. That's not what I said. I said that you can't be necessarily surprised if spam is classified as ham if your training set

RE: [SAtalk] Report points vs. header points discrepancy??

2003-03-30 Thread Paul Hutchings
anyone? regards, Paul -- Paul Hutchings Network Administrator, MIRA Ltd. Tel: 024 7635 5378, Fax: 024 7635 8378 mailto:[EMAIL PROTECTED] > -Original Message- > From: Paul Hutchings > Sent: 29 March 2003 18:10 > To: Spamassassin-Talk (E-mail) > Subject: [SAtalk] Report points vs. header

Re: [SAtalk] bayesian scoring

2003-03-30 Thread Ross Vandegrift
On Sun, Mar 30, 2003 at 12:42:26PM -0500, Theo Van Dinter wrote: > On Sun, Mar 30, 2003 at 11:52:47AM -0500, Chris Devers wrote: > > debug: bayes corpus size: nspam = 1289, nham = 29058 > > wow, that's way a lot of ham. I was curious so I just checked mine: 0.0000 7490