headers

[David Relson]

On Wed, 18 Feb 2004 09:01:36 -0600
Bill McClain wrote:

> On 18 Feb 2004 09:43:05 -0500
> Tom Anderson <tanderso at oac-design.com> wrote:
> 
> > But look at the "bogofilter resistant email" thread in the archives
> > for the email that I cannot get to score above 0.5.  I'm getting
> > more and more emails of this type.
> 
> I'm missing something here. I've gotten messages like those also, but
> 0.5 is very spammy for me. The last bogotune run suggested:
> 
>    spam_cutoff=0.079    
>    ham_cutoff=0.007      
> 
> Does this mean I have exceptionally well-behaved ham? I presume, from
> the discussion, that others are using much larger cutoff values.
> 
> -Bill

Hi Bill,

To answer your question, I'd say your spam_cutoff is unusually low.

I'm using ham_cutoff=0.45 and spam_cutoff=0.501 and get several unsures
every day.  I believe bogotune suggested 0.500001 for the spam_cutoff. 
However since I regularly see 0.500000 from lists at gnu.org, I decided
to use a slightly higher value.

By the way, spam_cutoff and ham_cutoff are only part of the story.  What
are robs, robx, and min_dev?  FWIW, my bogofilter.cf includes the
following:

### recommended ###
robx=0.549138
min_dev=0.465
robs=0.0178
spam_cutoff=0.941	# for 0.05% fp (11); expect 6.72% fn (1194).
#spam_cutoff=0.567	# for 0.10% fp (23); expect 3.60% fn (640).
#spam_cutoff=0.500	# for 0.20% fp (47); expect 1.18% fn (209).
ham_cutoff=0.376	

### overrides ###
min_dev=0.435		# manual override
spam_cutoff=0.501	# manual override



-- 
David Relson                   Osage Software Systems, Inc.
relson at osagesoftware.com       Ann Arbor, MI 48103
www.osagesoftware.com          tel:  734.821.8800