spam autolearn=not issue

[Matthew Baker]

man Mail::SpamAssassin::Conf

bayes_auto_learn_threshold_nonspam n.nn (default: 0.1)
            The score threshold below which a mail has to score, to be
fed into SpamAssassin's learning
            systems automatically as a non-spam message.

what's nspam and nham say from the out put of:

sa-learn --dump -p /etc/MailScanner/spam.assassin.prefs.conf |head

It looks as if it's learning it as not spam rather than not learning.

Brian Lewis wrote:
> I found that all my high scoring spam is doing autolearn=spam, but my ham
> is getting autolearn=not!
>
> spam autolearn=not
> -4.90 BAYES_00 Bayesian spam probability is 0 to 1%
>
>
> This message scored -4.90 but still has autolearn=not instead of
> autolearn=ham.  Where do I set it to autolearn=ham for say anything smaller
> than 0 score wise?
>
> MailScanner 4.29.7-1 using SpamAssassin 2.61 and Bayesian Filtering turned
> on.
>
> -------------------------- MailScanner list ----------------------
> To leave, send    leave mailscanner    to jiscmail at jiscmail.ac.uk
> For further info about MailScanner, please see the Most Asked
> Questions at    http://www.mailscanner.biz/maq/     and the archives
> at    http://www.jiscmail.ac.uk/lists/mailscanner.html

-------------------------- MailScanner list ----------------------
To leave, send    leave mailscanner    to jiscmail at jiscmail.ac.uk
For further info about MailScanner, please see the Most Asked
Questions at    http://www.mailscanner.biz/maq/     and the archives
at    http://www.jiscmail.ac.uk/lists/mailscanner.html