[Spambayes] Re: egregious patents on anti-spam techniques (Kaitlin Duck Sherwood)

[Rod Gilchrist]

Gary Robinson wrote:

>>Patent application on adaptive spam filtering:
>><http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=/net
>>ahtml/PTO/search-bool.html&r=3&f=G&l=50&co1=AND&d=PG01&s1=email.TTL.&OS=TTL/em
>>ail&RS=TTL/email>
>>    
>>
>
>I looked at this last night.
>
>I am not a lawyer, so don't go to the bank on what I say. And I didn't spend
>a huge amount of time on it.
>
>But I do have some experience with patents, and I do understand the
>spambayes approach and the gist of their approach. It is my impression that
>the patent does not have a scope that encompasses Graham-derived filters,
>because they do not calculate "first" and "second" "symantic anchors" as the
>term is used in Claim 1.
>  
>
Here's a quote from the background section of the application:

"Latent semantic analysis (LSA) is a method that automatically uncovers 
the salient semantic relationships between words and documents in a 
given corpus. Discrete words are mapped onto a continuous semantic 
vector space, in which clustering techniques may be applied."

Graham derived filters do map words into a 'continuous semantic vector 
space', namely the one dimensional vector
space of the range of [0.0, 1.0] of real numbers, and then 'clustering 
techniques' are applied. Normally clusters are
defined by hyperplanes in N-Space, but in one dimesion they would be 
threshold values. The two 'symantic anchors' are arguably cluster 
centers located at 0.0 and 1.0 (also known as ham and spam in 
Graham-derived filters).

In fact it is quite reasonable to describe a Graham-derived filter as 
having a 'ham anchor' that can
be described as a location in N-Space in which each token string 
describes a dimension and the
'clue' value for that string is the location of the anchor in that 
dimension. Connecting the 'ham anchor'
in N-Space with the 'spam anchor' in N'-Space with a normalized vector 
of unit length and positioning
a hyperplane at some position along the vector and perpendicular to it 
(i.e. a threshold) is dead normal
practice in 'clustering techniques'.

I'd like to write this patent off too, but to me it looks like it likely 
would apply to Graham-derived filters.

I'm not an expert in patents either, but I have a few issued ones of my own.

The good news is the filing date is June 14, 2001.

I'd like to suggest that it would be good to file a protest as Kaitlin 
suggested. There was certainly
work done in this area before June 14, 2001.  Does anyone have pointers 
they can pass along.

- Rod


Kaitlin Duck Sherwood wrote:

 > To protest a patent, you need to file prior art (within 60 days!) 
with the patent office.  See:
 > http://www.uspto.gov/web/offices/pac/mpep/documents/1900.htm
 > and
 > http://www.uspto.gov/web/offices/pac/mpep/documents/0600_610.htm#sect610

 > Patent application on adaptive spam filtering:
 ><http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=/netahtml/PTO/search-bool.html&r=3&f=G&l=50&co1=AND&d=PG01&s1=email.TTL.&OS=TTL/email&RS=TTL/email>

 > Patent application on whitelists, blacklists, challenge-response, and 
digital signatures used in spam-fighting:
 ><http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p
 >=1&u=/netahtml/PTO/srchnum.html&r=1&f=G&l=50&s1='20030009698'.PGNR.&OS=DN/20
 > 030009698&RS=DN/20030009698>