You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@spamassassin.apache.org by Michael Monnerie <m....@zmi.at> on 2006/03/02 14:21:19 UTC
SpamAssassin tested by lwn.net
http://lwn.net/SubscriberLink/173910/e7bf95a7cb044637/
They are wondering why bayes_99 is not given 5 points by default, as it
seems to have no FP.
mfg zmi
--
// Michael Monnerie, Ing.BSc --- it-management Michael Monnerie
// http://zmi.at Tel: 0660/4156531 Linux 2.6.11
// PGP Key: "lynx -source http://zmi.at/zmi2.asc | gpg --import"
// Fingerprint: EB93 ED8A 1DCD BB6C F952 F7F4 3911 B933 7054 5879
// Keyserver: www.keyserver.net Key-ID: 0x70545879
Re: OT Re: SpamAssassin tested by lwn.net
Posted by jdow <jd...@earthlink.net>.
From: "Gene Heskett" <ge...@verizon.net>
> On Friday 03 March 2006 17:56, jdow wrote:
>>From: "Kelson" <ke...@speed.net>
>>
>>> jdow wrote:
>>>> And of course, when reading BAYES_99 pronouncements one must ALWAYS
>>>> be aware that YMMV in big glowing radioactive Cherenkov Radiation
>>>> Blue letters is always presumed. Matt's note above proves it.
>>>
>>> Finally, a use for HTML in email!
>>>
>>> Though I'm not sure beta-particle-induced phosphorescence quite
>>> stacks up next to Cherenkov radiation...
>>
>>Having seen the latter there is NO comparison. Seeing a large lump of
>>"object" at the bottom of a large pool sitting there glowing quietly
>>in an unearthly blue is quite an experience. (And as a "Unified
>> Science" tracked engineering student at Univ of Mich the class all
>> did this as part of the Physical Chemistry course in semester 4. That
>> was an experience I'm not going to forget soon.)
>
> Humm, I wonder how long the leaves in the alpha badge stayed up?
Nah, safe installation, deep very clear pure water. Neutron radiation
would have been the significant danger. We all wore badges. But nothing
untowards happened. Exposure times were limited. We were NOT by any
stretch tickling the dragon's tail.
{^_-}
Re: OT Re: SpamAssassin tested by lwn.net
Posted by Gene Heskett <ge...@verizon.net>.
On Friday 03 March 2006 17:56, jdow wrote:
>From: "Kelson" <ke...@speed.net>
>
>> jdow wrote:
>>> And of course, when reading BAYES_99 pronouncements one must ALWAYS
>>> be aware that YMMV in big glowing radioactive Cherenkov Radiation
>>> Blue letters is always presumed. Matt's note above proves it.
>>
>> Finally, a use for HTML in email!
>>
>> Though I'm not sure beta-particle-induced phosphorescence quite
>> stacks up next to Cherenkov radiation...
>
>Having seen the latter there is NO comparison. Seeing a large lump of
>"object" at the bottom of a large pool sitting there glowing quietly
>in an unearthly blue is quite an experience. (And as a "Unified
> Science" tracked engineering student at Univ of Mich the class all
> did this as part of the Physical Chemistry course in semester 4. That
> was an experience I'm not going to forget soon.)
Humm, I wonder how long the leaves in the alpha badge stayed up?
I've not had that pleasure (of seeing cherenkov radiation) myself
anyplace but in a telescope image, but I did handle a bar of uranium
several times, using only some potholder mitts that weighed about 6-7
lbs each. That was in 1947 at the Iowa State Fair where the AEC had
set up a promo tent down in the middle of the horsetrack. They
normally kept it in a lead casket that probably weighed a ton or so,
and had live geiger counters all over the place, Pick it up out of the
casket and all the counters around sounded like ripping canvas.
Since I was only 12 at the time, its weight did impress me as it was
obviously heavier than I thought a lead bar that size would be, about
50 pounds counting the potholders. Thinking back on that, I hung
around thinking it was cool, but probably got more than a years dose in
that 4 days I made it to the fair. And amazingly, I'm still around,
not that it makes any great difference to anybody but me. Next year
they didn't bring it, just the paper propaganda promoting atomic
energy. Safety considerations I was told when I asked. Yeah sure.
>{^_-} Joanne
--
Cheers, Gene
People having trouble with vz bouncing email to me should add the word
'online' between the 'verizon', and the dot which bypasses vz's
stupid bounce rules. I do use spamassassin too. :-)
Yahoo.com and AOL/TW attorneys please note, additions to the above
message by Gene Heskett are:
Copyright 2006 by Maurice Eugene Heskett, all rights reserved.
Re: OT Re: SpamAssassin tested by lwn.net
Posted by jdow <jd...@earthlink.net>.
From: "Kelson" <ke...@speed.net>
> jdow wrote:
>> And of course, when reading BAYES_99 pronouncements one must ALWAYS be
>> aware that YMMV in big glowing radioactive Cherenkov Radiation Blue
>> letters is always presumed. Matt's note above proves it.
>
> Finally, a use for HTML in email!
>
> Though I'm not sure beta-particle-induced phosphorescence quite stacks
> up next to Cherenkov radiation...
Having seen the latter there is NO comparison. Seeing a large lump of
"object" at the bottom of a large pool sitting there glowing quietly
in an unearthly blue is quite an experience. (And as a "Unified Science"
tracked engineering student at Univ of Mich the class all did this as
part of the Physical Chemistry course in semester 4. That was an experience
I'm not going to forget soon.)
{^_-} Joanne
OT Re: SpamAssassin tested by lwn.net
Posted by Kelson <ke...@speed.net>.
jdow wrote:
> And of course, when reading BAYES_99 pronouncements one must ALWAYS be
> aware that YMMV in big glowing radioactive Cherenkov Radiation Blue
> letters is always presumed. Matt's note above proves it.
Finally, a use for HTML in email!
Though I'm not sure beta-particle-induced phosphorescence quite stacks
up next to Cherenkov radiation...
--
Kelson Vibber
SpeedGate Communications <www.speed.net>
Re: SpamAssassin tested by lwn.net
Posted by jdow <jd...@earthlink.net>.
From: "Matt Kettler" <mk...@comcast.net>
> Michael Monnerie wrote:
>> http://lwn.net/SubscriberLink/173910/e7bf95a7cb044637/
>>
>> They are wondering why bayes_99 is not given 5 points by default, as it
>> seems to have no FP.
>
> Statisticaly speaking, 1% of BAYES_99 hits should be nonspam.In reality,
> it does a lot better than that.
>
> However, in the SA 3.1.0 set3 mass checks it still managed to match
> about 21 messages in the nonspam test set:
>
> OVERALL% SPAM% HAM% S/O RANK SCORE NAME
> 176869 123778 53091 0.700 0.00 0.00 (all messages)
> 60.712 86.7351 0.0396 1.000 0.90 3.50 BAYES_99
>
>
> SA's scores aren't based on human assumptions about how the rules
> behave. They are based on real-world testing and a perceptron
> score-fitting system that accounts not only for the hit-rate of the
> rule, but also for the combinations of rules that it tends to match
> with. Often the reality is a lot more complex than you think.
And of course, when reading BAYES_99 pronouncements one must ALWAYS be
aware that YMMV in big glowing radioactive Cherenkov Radiation Blue
letters is always presumed. Matt's note above proves it.
{^_-}
Re: SpamAssassin tested by lwn.net
Posted by Matt Kettler <mk...@comcast.net>.
Michael Monnerie wrote:
> http://lwn.net/SubscriberLink/173910/e7bf95a7cb044637/
>
> They are wondering why bayes_99 is not given 5 points by default, as it
> seems to have no FP.
Statisticaly speaking, 1% of BAYES_99 hits should be nonspam.In reality,
it does a lot better than that.
However, in the SA 3.1.0 set3 mass checks it still managed to match
about 21 messages in the nonspam test set:
OVERALL% SPAM% HAM% S/O RANK SCORE NAME
176869 123778 53091 0.700 0.00 0.00 (all messages)
60.712 86.7351 0.0396 1.000 0.90 3.50 BAYES_99
SA's scores aren't based on human assumptions about how the rules
behave. They are based on real-world testing and a perceptron
score-fitting system that accounts not only for the hit-rate of the
rule, but also for the combinations of rules that it tends to match
with. Often the reality is a lot more complex than you think.
Re: SpamAssassin tested by lwn.net
Posted by jdow <jd...@earthlink.net>.
It is graded 5 here. I overrode the perceptron score. So far I have not seen
a false positive that got a BAYES_99 score. I've seen a very small number of
false negatives in spite of the BAYES_99 score.
{^_^}
----- Original Message -----
From: "Martin Hepworth" <ma...@solid-state-logic.com>
>
> Seems to produce != doesn't ever.
>
> Depends on your config, but I think the developers err on the side of
> caution a little and don't have single test score that would trigger go over
> the default 'is spam' limit.
>
> Could be wrong - frequently am...
>
> --
> Martin Hepworth
>> -----Original Message-----
>> From: Michael Monnerie [mailto:m.monnerie@zmi.at]
>>
>> http://lwn.net/SubscriberLink/173910/e7bf95a7cb044637/
>>
>> They are wondering why bayes_99 is not given 5 points by default, as it
>> seems to have no FP.
>>
>> mfg zmi
RE: SpamAssassin tested by lwn.net
Posted by Martin Hepworth <ma...@solid-state-logic.com>.
Seems to produce != doesn't ever.
Depends on your config, but I think the developers err on the side of
caution a little and don't have single test score that would trigger go over
the default 'is spam' limit.
Could be wrong - frequently am...
--
Martin Hepworth
Snr Systems Administrator
Solid State Logic
Tel: +44 (0)1865 842300
> -----Original Message-----
> From: Michael Monnerie [mailto:m.monnerie@zmi.at]
> Sent: 02 March 2006 13:21
> To: users@spamassassin.apache.org
> Subject: SpamAssassin tested by lwn.net
>
> http://lwn.net/SubscriberLink/173910/e7bf95a7cb044637/
>
> They are wondering why bayes_99 is not given 5 points by default, as it
> seems to have no FP.
>
> mfg zmi
> --
> // Michael Monnerie, Ing.BSc --- it-management Michael Monnerie
> // http://zmi.at Tel: 0660/4156531 Linux 2.6.11
> // PGP Key: "lynx -source http://zmi.at/zmi2.asc | gpg --import"
> // Fingerprint: EB93 ED8A 1DCD BB6C F952 F7F4 3911 B933 7054 5879
> // Keyserver: www.keyserver.net Key-ID: 0x70545879
**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
This footnote confirms that this email message has been swept
for the presence of computer viruses and is believed to be clean.
**********************************************************************