I've now had this version running for quite some time, about 3 months.   My 
rebuild log indicates that I have a corpus weight of aobut 1.3 (spam heavy), 
but NOTHING is not flagged as spam.  Literally, unless it's whitelisted, 
it's flagged as spam, and typically it has somewhere between .9 and 1 as 
certainty.

It started this way and has never changed.   My users have sent a few 
hundred "errors" to the system as have I, but it doesn't seem to have any 
effect.

My previous version was quite effective at learning the difference.   This 
one seems to learn nothing.  Everything is spam and always has been.

I'm thinking of just shutting off the heuristics, as random flagging would 
be more accurate.

Anyone have suggestions as to what might be wrong, or how to fix it?



------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and 
threat landscape has changed and how IT managers can respond. Discussions 
will include endpoint security, mobile security and the latest in malware 
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Assp-user mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/assp-user

Reply via email to