after reading all in Bayesian docs , I can't understand If I have a possibility 
to score exactly
baysValencePB  value in all situations , I understood there is no way now.

Graziano
> ASSP development mailing list<[email protected]>
> schreibt:
>> even if I received this too
>> Mar-15-12 05:48:01 id-33180-00030 213.92.5.228<[email protected]>  to:
>> [email protected] Bayesian Check [scoring:42] - Prob: 0.99976 =>  spam;
>>
>> 42 instead of 43 with baysConf 0 , baysProbability 0.6 (?)
> The GUI text for baysProbability says:
> baysProbability: Messages with spam-probability below or equal this
> threshold are considered Ham. Recommended '0.6'.
>   An resulting Spam-Probability above this value is multiplied with
> baysValencePB_local or baysValencePB to get the penaltybox scoring
> value for the IP- and message score. In other words, the penaltybox
> scoring value is weighted by the Spam-Probability in case Spam is
> detected.
>
>
> ------------------------------------------------------------------------------
> This SF email is sponsosred by:
> Try Windows Azure free for 90 days Click Here
> http://p.sf.net/sfu/sfd2d-msazure
> _______________________________________________
> Assp-test mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/assp-test
>


------------------------------------------------------------------------------
This SF email is sponsosred by:
Try Windows Azure free for 90 days Click Here 
http://p.sf.net/sfu/sfd2d-msazure
_______________________________________________
Assp-test mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/assp-test

Reply via email to