|time||29 minutes plus 10/30s|
The first round started at 16:00 UTC.
|1||Zen19S||W13R B15R||B16R W17R||W12R||B11R||B14R||7||23||23||Winner|
|2||AyaMC||B03R W05R||W12R||W11R B17R||B14R||B16R||5||26||12|
|3||DolBaram||W06R B07R||B02R||W14R||W13R B15R||B11R||4||26||7|
|4||NiceGo19N||B02R||B01R W07R||B04R||B16R||W13R B15R||3||23||2|
|5||HiraBot||W01R||W04R||B03R W05R||W06R||W12R B17R||2||23||0|
|6||MCark2||W04R||W06R||W01R||B03R W05R||B02R W07R||0||26||0|
Black won 12 games and White won 9 games
Six players entered. They were all regular players in these events, but one, NiceGo19N, was Detlef Schmicker's latest version of oakfoam, using a Convolutional Neural Network. The possibilty of using a CNN to play Go recently been described as promising, so it is good to see one such engine developed already. See this paper for more information.
All 21 games went smoothly, without disputes or disconnections, and ended in resignations. Each player beat all those listed below it in the cross-table.
|HiraBot vs AyaMC|
In round 4, HiraBot and AyaMC managed to play 34 moves in ten seconds. The moves themselves, shown to the right, seem unremarkable and sensible. I wonder how they both achieved this - do they both have joseki books? Do they play their joseki without reference to the other corners?
In round 6, NiceGo19N beat HiraBot. It has lost I think all its previous 19×19 games with HiraBot. This was remarked on by Aja Huang: "Congrats on oakfoam's significant improvement with the CNN. The game oakfoam beat HiraBot[1d] is very nice." link to game
Players receive points for the 2015 Annual KGS Bot Championship as follows: