Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Comments of latest SSDF list

Author: Rolf Tueschen

Date: 09:25:28 05/25/02

Go up one level in this thread


On May 25, 2002 at 04:36:42, Uri Blass wrote:

>On May 25, 2002 at 03:55:58, Sandro Necchi wrote:
>
>>THE SSDF RATING LIST 2002-05-22   86121 games played by  240 computers
>>                                           Rating   +     -  Games   Won  Oppo
>>                                           ------  ---   --- -----   ---  ----
>>   1 Fritz 7.0 256MB Athlon 1200 MHz         2730   33   -31   494   64%  2626
>>   2 Chess Tiger 14.0 CB 256MB Athlon 1200   2722   33   -32   477   63%  2626
>>   3 Gambit Tiger 2.0  256MB Athlon 1200     2720   34   -33   441   62%  2635
>>   4 Deep Fritz 256MB Athlon 1200 MHz        2714   33   -32   482   63%  2623
>>   5 Shredder 6.0  256MB Athlon 1200 MHz     2713   35   -34   432   64%  2611
>>   6 Junior 7.0  256MB  Athlon 1200 MHz      2693   31   -31   511   57%  2641
>>
>>Shredder 6.32 (CB version) is 27 points behind Fritz 7
>
>
>1)Shredder6.32 is 1 elo behind Deep Fritz.
>
>>
>>   7 Rebel Century 4.0 256MB Athlon 1200 MHz 2684   34   -32   470   64%  2585
>>   8 Shredder 5.32  256MB Athlon 1200 MHz    2670   31   -30   536   56%  2624
>>   9 Gandalf 4.32h  256MB Athlon 1200 MHz    2653   34   -33   430   54%  2625
>>  10 Deep Fritz  128MB K6-2 450 MHz          2652   23   -23   945   61%  2570
>>  11 Gandalf 5.1  256MB Athlon 1200 MHz      2646   29   -28   595   57%  2594
>>  12 Gandalf 5.0  256MB Athlon 1200 MHz      2642   49   -50   202   46%  2673
>>  13 Gambit Tiger 2.0  128MB K6-2 450 MHz    2640   30   -29   592   66%  2521
>>  14 Fritz 7.0  128MB K6-2 450 MHz           2631   45   -44   250   56%  2592
>>  14 Junior 7.0  128MB K6-2 450 MHz          2631   27   -26   739   67%  2507
>>  16 Chess Tiger 14.0 CB 128MB K6-2 450 MHz  2630   28   -27   652   62%  2541
>>  16 Shredder 6.0 UCI 128MB K6-2 450 MHz     2630   65   -62   124   57%  2578
>>  18 Fritz 6.0  128MB K6-2 450 MHz           2623   23   -22  1014   63%  2529
>>
>>Shredder 6.0 (UCI version) is 1 point behind Fritz 7
>>
>
>2)Shredder6 (UCI version) is 22 elo behind Deep Fritz.
>
>> SSDF comment
>>
>>We have played 124 games with the UCI-version of
>>Shredder 6.0 K6-2 450 MHz, using the opening book of
>>Sandro Necchi. So far the rating is 2630. With so few
>>games it's difficult to draw any conclusions concerning
>>which opening book Shredder 6.0 might benefit most from.
>>
>>My comment:
>>
>>What is 26 points difference?
>>
>>Apparently NOTHING:-))
>>
>>No other comments are needed.
>>
>>Sandro Necchi
>
>3)My comment:
>
>You are absulutely right.
>
>26 elo difference can be translated to 21 elo difference for the other side so
>they mean nothing.
>
>Uri

If people would only understand that the "list" is not a ranking but a
presentation of "nothings", the SSDF persons, who are investing so much precious
time personally, could  be moved to make a completely new and fair design for
their testing. The actual list is bogus because the parts which interest the
most have no statistical meaning, those parts however who have a certain meaning
are no longer interesting for the public. But this is the fault of SSDF alone
only at first glance, they are at the mercy of the industry because their system
would function _in the long run_, but before it could succeed, the brand new
versions of the programs appear. But this again leads to a permanent circle of
investigating and presenting "nothing".

Two possibilities. The SSDF is completely unaware of this. Or the software
industry is the real chief in Sweden. Ah, yes, I forgot the interdependencies.
It is often said that this "ranking" list is better than nothing, but this
itself is a logical fallacy. I am sure that if the SSDF people would look
through this they would stop this. And there are certainly better designs for
testing such products with so nigh expire dates.

And besides I am absolutely conform with Sandro Necchi that the commentary about
the influence of his book is meaningless, because there is no way (what SSDF
tried in their commentary) to extract logic in or out of a statistical nothing,
but that was already what Dr. Tuerke said.

Rolf Tueschen



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.