I picked one game randomly: zen/FuegoEx-091108-8c-20091125000443.sgf<div><div><br></div><div>There are no comments on opponents move. Aren&#39;t you using</div><div>pondering? It could be useful to dump Fuego&#39;s pondering state</div>
<div>when the opponent plays.</div><div><br></div><div>Move 74 (W N9) is valued at 0.59 which seems too high.</div><div>This is confirmed by the significant drop to 0.47 at the</div><div>next move.</div><div><br></div><div>
Move 170 W O17 can be considered as the losing move. It should be at J17.</div><div><br></div><div>Jean-loup</div><br><div class="gmail_quote">2009/11/27 Martin Mueller <span dir="ltr">&lt;<a href="mailto:mmueller@ualberta.ca">mmueller@ualberta.ca</a>&gt;</span><br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div style="word-wrap:break-word"><div>More than the 9x9, the 19x19 games show a steep gradient in results by playing strength. FuegoEx wins most games against weaker programs, but loses almost all games against stronger opposition, including 37 in a row against Zen :(</div>
<div><br></div><div><span style="font-family:&#39;Helvetica Neue&#39;;color:rgb(0, 16, 0)"></span><div><span style="font-family:&#39;Helvetica Neue&#39;;color:rgb(0, 16, 0)"><table cellspacing="0" style="border-top-style:solid;border-right-style:solid;border-bottom-style:solid;border-left-style:solid;border-top-width:1px;border-right-width:1px;border-bottom-width:1px;border-left-width:1px;font-size:13px">
<tbody><tr bgcolor="#ffffff"><td>CrazyStone-1102-2c</td><td>2247</td><td>3 / 7</td><td>42.86</td></tr><tr bgcolor="#e0e0e0"><td>mfgo12-605-2c</td><td>2368</td><td>5 / 22</td><td>22.73</td></tr><tr bgcolor="#ffffff"><td>CrazyStone-10-64</td>
<td>2444</td><td>0 / 4</td><td>0.00</td></tr><tr bgcolor="#e0e0e0"><td>Zengg-4x4c-tst</td><td>2569</td><td>0 / 37</td><td>0.00</td></tr></tbody></table></span><div><br></div></div></div><div>I put games, including the search log in sgf comments, onto</div>
<a href="http://www.cs.ualberta.ca/~mm" target="_blank">http://www.cs.ualberta.ca/~mm</a><font color="#000000" size="4"><span style="background-color:transparent;font-size:16px">ueller/temp/FuegoEx-091108-8c</span></font><div>
<br></div><div>We are looking for insights about systematic weaknesses, especially of the game-losing kind, for specific test cases of blunders to add to the performance or regression test suites, for grossly misevaluated positions (program thinks it is winning but is losing, and vice versa), and other useful information.</div>
<div><br></div><div>Thanks</div><div><br></div><font color="#888888"><div><span style="white-space:pre">	</span>Martin</div></font></div><br>------------------------------------------------------------------------------<br>

Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day<br>
trial. Simplify your report design, integration and deployment - and focus on<br>
what you do best, core application coding. Discover what&#39;s new with<br>
Crystal Reports now.  <a href="http://p.sf.net/sfu/bobj-july" target="_blank">http://p.sf.net/sfu/bobj-july</a><br>_______________________________________________<br>
fuego-devel mailing list<br>
<a href="mailto:fuego-devel@lists.sourceforge.net">fuego-devel@lists.sourceforge.net</a><br>
<a href="https://lists.sourceforge.net/lists/listinfo/fuego-devel" target="_blank">https://lists.sourceforge.net/lists/listinfo/fuego-devel</a><br>
<br></blockquote></div><br></div>