Hi all, Here's a debug of the Bayes portion of an SA run on an email I recently received. Individual token scores range from 0.01 to 0.91, but the final Bayes score is 0.0002!
How does the final score come out so low? I thought it was computed from the arithmetic mean of all the token scores. Or is there something else going on? (This is SA 2.63 with mostly auto-learned Bayes DB.) debug: bayes token 'H*c:US-ASCII' => 0.0178547475635557 debug: bayes token 'Bicycle' => 0.0256190476190476 debug: bayes token '790' => 0.0256190476190476 debug: bayes token 'Ranger' => 0.0256190476190476 debug: bayes token 'H*r:sk:MDaemon' => 0.0307070478260523 debug: bayes token 'Swiss' => 0.0318769084000459 debug: bayes token 'wondering' => 0.0348539919377274 debug: bayes token 'H*M:swissinfo' => 0.958 debug: bayes token 'HX-Spam-Processed:Jun' => 0.0488394594086035 debug: bayes token 'HX-Spam-Processed:2004' => 0.0488394594086035 debug: bayes token 'N:HX-Spam-Processed:NNNN' => 0.0488394594086035 debug: bayes token 'HX-Spam-Processed:Fri' => 0.0489090909090909 debug: bayes token 'sk:freemai' => 0.0489090909090909 debug: bayes token 'UD:swissinfo.org' => 0.0489090909090909 debug: bayes token 'Dreaming' => 0.0489090909090909 debug: bayes token 'N:H*r:NNN.NNN.N' => 0.0678682786640362 debug: bayes token 'Account' => 0.0700337092878614 debug: bayes token 'H*c:plain' => 0.0739706913470909 debug: bayes token 'HTo:D*domain.com' => 0.0792429905673705 debug: bayes token 'HTo:U*sales' => 0.0793161570264447 debug: bayes token 'H*M:org' => 0.0798685713630609 debug: bayes token 'canadian' => 0.914711110379178 debug: bayes token 'Get' => 0.912333215337874 debug: bayes token 'dan' => 0.0889253724913709 debug: bayes token 'canada' => 0.909210055764283 debug: bayes token 'H*r:sk:[EMAIL PROTECTED]' => 0.0958329013747179 debug: bayes token 'dear' => 0.0962159069784254 debug: bayes token 'Toronto' => 0.868353738275702 debug: bayes: score = 0.000256655992644517 Pierre Thomson BIC
