Ways to trick the lexer

[Thomas Anderson]

On Sat, 2007-06-09 at 10:38 +0100, John G Walker wrote:
> > X-Bogosity: No, tests=bogofilter, spamicity=0.684388, version=1.1.5
> 
> The message has been given a spamicity of 68%. 
> 
> I would suggest that your cutoff point is set too high. Do you actually
> get ham with such a high spamicity? If not, you should bring the cutoff
> point down. I've got mine set at 60% and don't get false positives,

Agreed.  Here's mine:

robx=0.41, robs=0.2, min_dev=0.2, spam_cutoff=0.42, ham_cutoff=0.1

I don't get false positives either.  New/random tokens are unsure, but
just barely.  The rest of the message/headers sends it easily over the
edge.  I get maybe 3-4 unsure messages a day (almost all spam) and 1-2
false negatives out of well over a hundred.  I'm extremely pleased with
this performance.  In my experience, a spam cutoff much above robx is
not a good idea.

Tom