On 2/28/02 12:02 PM, "Gunter Ohrner" <[EMAIL PROTECTED]> wrote:
> Maybe SA needs to know some additional non-spam tests to compensate for
> successful spam tests? The current scores look to me as if the GA tried its
> best to avoid false positives which unfortunately contained some
> spam-specifi
Yes, I completely agree. I'll be working on "hinting" the rules and having
the mutation part of the GA tend to move scores in the right direction after
I get 2.11 out.
C
On 2/28/02 9:36 AM, "Greg Ward" <[EMAIL PROTECTED]> wrote:
> Executive summary: I think that unconstraining the GA was an in
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Am Thursday, 28. February 2002 18:36 schrieb Greg Ward:
> First, I ran the 59 existing true positives through SA 2.1, looking for
> any that scored < 5. There were four; three of them slipped by because
> of DEAR_SOMEBODY scoring -4.4, and the fourth
At 12:36 PM 2/28/2002 -0500, Greg Ward wrote:
>Here are my corrected scores, in no particular order. These scores were
>derived using a highly sophisticated natural intelligence algorithm,
>namely gut instinct:
>
> score DEAR_SOMEBODY 1.0 # was -4.4
> score CASHCASHCASH1.
Well, the bugs in SA 2.0 just got to be too annoying, so I've upgraded
one box to SA 2.1 -- never mind what people say about the new scores in
2.1. However, I decided to do a little experiment to see how the new
scores stack up against my own personal spam corpus. It isn't much; on
the one hand
