Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: An Alternative Method

Author: Ricardo Gibert

Date: 00:35:49 05/08/05

Go up one level in this thread


On May 07, 2005 at 09:14:27, Uri Blass wrote:

>On May 07, 2005 at 05:46:32, Claude Le Page wrote:
>
>>I suggest another method:
>>consider the famous game Atars-Tomson (it is in every database)
>>1 e4 e5 2 Nf3 f5 3 Bc4 fxe4 4 Nxe5 Qg5 5 d4 Qxg2 6 Qh5+ g6 7 Bf7+ Kd8
>>8 Bxg6 Qxh1+ 9 Ke2 c6 10 Nc3 Kc7 11 Bf4 Qxa1 12 Nxd7+!! (every "good" engine
>>finds it)Kxd7 13 Qf5+ Kd8 14 Qxf8+ Kd7 15 Bf5#
>>The interesting point is elsewhere:On 12...Kd8 (best!)there is #14 (generally
>>announced as #18 )
>>There are at least 3 mates completely different: that of Junior7 and that of
>>Shredder9 have nothing in common (although both are #14 announced as#18)
>>It would be interesting to compare on his position PVs of Patriot , Toga and so
>>on
>>As I am not Programmer , Just Analyst ( in my previous job as in my chess life )
>>this method is easier for me
>>Surely , the position I quoted is not unique , and you could easily find other
>>ones
>
>What you suggest is not another method.
>
>Of course analyzing positions can practically help to prove that 2 engines are
>clones and I think that the test to detect clones should include also secret
>positions to see if the move of the program is the same as another open source
>program.
>
>I think that it is not productive to talk here about the exact methods to
>discover clones because it can help cloners and it is better to talk about it by
>email.
>
>Uri

How about a dozen test positions where the position is blocked and one move is
as good as another. Only a clone would show the same PV in all or most of the
test positions.

Such positions would be more effective than the usual test positions that often
have just one line that is definitely best.

I don't really know if this would work well. It's just a thought.

BTW, you wouldn't need to keep the positions secret. Just use a different set
each time the test is performed.

Here is an example comparing Ruffian with SOS:

[D]r1b1k2r/8/p1p1p1p1/PpPpPpPp/1P1P1P1P/8/8/R1B1K2R w KQkq -

Ruffian 1.0.1  UCI 13 MB:
D1  00:00  0.08   Bb2
D1  00:00  0.10   Bd2
D2  00:00  0.01   Bd2 Bd7
D3  00:00  0.07   Bd2 Bd7 Ke2
D4  00:00  0.01   Bd2 Bd7 Ke2 Ke7
D5  00:00  0.02   Bd2 Bb7 Ke2 0-0-0 Rhg1
D6  00:00  0.01   Bd2 Bb7 Ke2 0-0-0 Rhg1 Rhf8
D7  00:00  0.02   Bd2 Bb7 Ke2 0-0-0 Rhg1 Rhf8 Rac1
D8  00:00  0.00   Bd2 Bb7 Rg1 0-0-0 Rc1 Rhf8 Rg3 Rf7
D8  00:00  0.01   Be3 Bb7 Rh2 0-0-0 Rc2 Rhf8 Rd1 Rf7
D9  00:00  0.01   Be3 Bb7 Rh2 0-0-0 Rc2 Rhf8 Rac1 Rf7 Rd1
D10  00:00  0.01   Be3 Bb7 Rh2 0-0-0 Rc2 Rhf8 Rac1 Rf7 Rd1 Re7
D11  00:00  0.00   Be3 Bb7 Rh2 0-0-0 Rc2 Rhf8 Rac1 Rf7 Rd1 Re7 Rd3
D11  00:00  0.01   Bd2 Bb7 Rg1 0-0-0 Ke2 Rhf8 Rac1 Rf7 Rg3 Re7 Rd3
D12  00:00  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8
D13  00:00  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Kd1
D14  00:00  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Kd1 Re7
D15  00:00  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Kd1 Re7 Ke1
D16  00:00  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Kd1 Re7 Ke1
Rf7
D17  00:01  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Kd1 Re7 Bb2
Rf7 Bc3
D18  00:01  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Rdd2 Ke7 Rd1
Ke8 Rd3 Re7
D19  00:03  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Rdd2 Ke7 Rd1
Ke8 Rd3 Re7 Kd1
D20  00:04  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Rdd2 Ke7 Rd1
Ke8 Rd3 Re7 Kd1 Rf7
D21  00:06  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Rdd2 Ke7 Rd1
Ke8 Rd3 Re7 Kd1 Rf7 Ke1
D22  00:08  0.02   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rd1 Rf7 Rd3 Ke8 Rdd2 Ke7 Rd1
Ke8 Rc1 Re7 Ra1 Rf7 Rd1 Re7
D23  00:33  0.03   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rc1 Rd7 Kd1 Kd8 Kc2 Rff7 Rd1
Rfe7 Kb3 Re8 Ree1 Ree7 Re3 Re8 Re2
D24  00:41  0.03   Bd2 Bb7 Rh2 Rf8 Re2 Ke7 Bc3 Rad8 Rc1 Rd7 Kd1 Kd8 Kc2 Rff7 Rd1
Rfe7 Kb3 Re8 Ree1 Ree7 Re3 Re8 Re2 Rf8


SOS.3 for Arena  UCI 13 MB:
D1  00:00  0.35   Rf1
D2  00:00  0.38   Rf1
D3  00:00  0.35   Bb2 Rb8 Rd1
D4  00:00  0.34   Rf1 Bd7 Be3 0-0-0
D5  00:00  0.30   Rf1 Bd7 Be3 0-0-0 Rd1
D6  00:00  0.22   Rf1 Bb7 Be3 0-0-0 Rd1 Kd7
D7  00:00  0.15   Rf1 Bb7 Be3 0-0-0 Rd1 Kd7 Ke2
D8  00:00  0.16   Rf1 Bb7 Be3 0-0-0 Rd1 Kd7 Ke2
D9  00:00  0.09   Be3 Bb7 Rd1 0-0-0
D10  00:00  0.09   Be3 Bb7 Rd1 0-0-0 Rf1 Kd7 Ke2 Rhf8 Kd3
D10  00:00  0.20   Be3 Bb7 Rd1 0-0-0 Rf1 Kd7 Ke2 Rhf8 Kd3
D10  00:00  0.27   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhe1 Rhf8 Kd3
D11  00:00  0.09   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhe1 Rh7 Kd3 Re7 Re2
D12  00:00  0.09   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhe1 Rh7 Kd3 Re7 Re2
D12  00:00  0.20   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhe1 Rh7 Kd3 Re7 Re2
D13  00:01  0.16   Be3 Bb7 Rd1 0-0-0 Ke2 Kd7 Rh3 Rhf8 Rf3 Rf7
D14  00:01  0.16   Be3 Bb7 Rd1 0-0-0 Ke2 Kd7 Rh3 Rhf8 Rf3 Rf7 Kd3 Ke7 Re1
D14  00:02  0.27   Be3 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhg1 Rhg8 Kd3 Ke7 Rg2
D14  00:02  0.28   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhf1 Rh7 Kd3 Re7 Rd2 Ree8 Re2
D15  00:05  0.20   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhe1 Rhf8 Kd3 Rde8 Re2 Rf7 Rde1
D16  00:05  0.20   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhe1 Rhf8 Kd3 Rde8 Re2 Rf7 Rdd2
Ree7 Rc2
D16  00:06  0.24   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhe1 Rhf8 Kd3 Rde8 Re2 Rf7 Rdd2
Ree7 Rc2
D16  00:07  0.27   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhf1 Rhf8 Kd3 Rf7 Rd2 Re8 Rf3 Rc8
Rc2
D16  00:08  0.28   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhe1 Rhg8 Rd2 Rge8 Kd3 Rc8
D17  00:22  0.24   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhf1 Rhf8 Kd3 Rf7 Rd2 Rc8 Rff2
D18  00:24  0.24   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhf1 Rhf8 Kd3 Rf7 Rd2 Rc8 Rff2 Rg7
Rd1 Re8 Re1 Rd8 Rfe2
D18  00:26  0.25   Be3 Bb7 Rd1 0-0-0 Ke2 Kc7 Rhg1 Rh7 Kd3 Rc8 Rd2 Rg7 Rb2 Re7
Rf1 Rce8 Rf3 Rf7 Rc2 Rfe7 Rb2
D18  00:30  0.26   Be3 Bb7 Ke2 Rf8 Rad1 0-0-0 Rhf1 Kc7 Kd3 Rf7 Rd2 Rc8 Rff2 Rg7
Rfe2 Re7
D18  00:35  0.27   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhe1 Rhf8 Kd3 Rf7 Re2 Rc8 Rdd2 Ke7
Re3 Rd8 Bc3 Rff8 Ree2
D18  00:37  0.28   Bb2 Bb7 Rd1 0-0-0 Ke2 Kd7 Rhf1 Rde8 Kd3 Rh7 Rd2 Rhe7 Bc3 Rf8
Rf3 Rff7 Re3 Kc7 Rde2 Rd7

It's obvious they are not clones of one another.




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.