Author: Dann Corbit
Date: 11:51:47 12/15/03
Go up one level in this thread
On December 15, 2003 at 14:09:34, martin fierz wrote: >On December 15, 2003 at 13:58:02, Dann Corbit wrote: > >>Number of tests: 183 >>Max score: 183 >>Engines score: 165 >>Number with full score: 165 >>Found in: 1 sec = 28, 2 sec = 11, 5 sec = 29, 10 sec = 20, 30 sec = 30, 1 min = >>9, 2 min = 12, 5 min = 17, 10 min = 4, 30 min = 5, >>Time used for tests (wrong answer=900s): 27361s >> >>Positions with error (id): >>ECM.1068, ECM.1197, ECM.1204, ECM.1217, ECM.1227, >>ECM.1229, ECM.1265, ECM.1273, ECM.1294, ECM.1308, ECM.1314, >>ECM.1438, ECM.1533, ECM.1592, ECM.1612, ECM.1617, ECM.1621, >>ECM.1622 > >and always the same question... hardware?? 950 MHz AMD Athlon. Here are the output lines for the missed positions. It shows at least one clear bug in the test set, and also a clear bug in Crafty's EPD output (it violates the EPD standard): ECMGCP.out ( 28): r1bq1rk1/pp2bp1p/2p2np1/3p2B1/3P4/2NQ2N1/PPP2PPP/4RRK1 w - - acd 15; acn 200032643; acs -1; bm Rxe7; ce 65; id "ECM.1068"; pm Qe2; pv Qe2 Be6 f4 Re8 Qd3 Nd7 Bxe7 Rxe7 f5 Bxf5 Nxf5 Rxe1 Rxe1 gxf5 Qxf5 Qh4 Qf2; ECMGCP.out ( 58): 2b3k1/p4ppp/7q/2Q5/8/P3r1P1/1r4BP/R3R1K1 b - - acd 12; acn 253011707; acs -1; bm Bb7; ce -32748; id "ECM.1197"; pm Rxg2+; pv Rxg2+ Kxg2 Bb7+ Kf2 Rf3+ Kg2 Rxa3+ Kg1 Rxg3+ Kf1 Qh3+ Ke2 Rg2+ Kd1 Qb3+ Kc1 Qb2+ Kd1 Rd2#; Crafty found an alternate move that leads to sure checkmate. Rxg2+ must be considered as an alternate solution. This position also illustrates the bug in crafty's EPD analysis. The EPD standard is very clear: "16.2.5.6: Opcode "ce": centipawn evaluation The opcode "ce" indicates the evaluation of the indicated position in centipawn units. It takes a single operand, an optionally signed integer that gives an evaluation of the position from the viewpoint of the active player; i.e., the player with the move. Positive values indicate a position favorable to the moving player while negative values indicate a position favorable to the passive player; i.e., the player without the move. A centipawn evaluation value close to zero indicates a neutral positional evaluation. Values are restricted to integers that are equal to or greater than -32767 and are less than or equal to 32766. A value greater than 32000 indicates the availability of a forced mate to the active player. The number of plies until mate is given by subtracting the evaluation from the value 32767. Thus, a winning mate in N fullmoves is a mate in ((2 * N) - 1) halfmoves (or ply) and has a corresponding centipawn evaluation of (32767 - ((2 * N) - 1)). For example, a mate on the move (mate in one) has a centipawn evaluation of 32766 while a mate in five has a centipawn evaluation of 32758. A value less than -32000 indicates the availability of a forced mate to the passive player. The number of plies until mate is given by subtracting the evaluation from the value -32767 and then negating the result. Thus, a losing mate in N fullmoves is a mate in (2 * N) halfmoves (or ply) and has a corresponding centipawn evaluation of (-32767 + (2 * N)). For example, a mate after the move (losing mate in one) has a centipawn evaluation of -32765 while a losing mate in five has a centipawn evaluation of -32757. A value of -32767 indicates an illegal position. A stalemate position has a centipawn evaluation of zero as does a position drawn due to insufficient mating material. Any other position known to be a certain forced draw also has a centipawn evaluation of zero." The first paragraph shows clearly that the analysis is "from the viewpoint of the active player" and therefore, the negative score is wrong. I realize that all the professional programs score in this way. But all of them are wrong too. ECMGCP.out ( 62): r2r2k1/1bqpbpp1/ppn1p2p/2p1P1N1/P1B2B2/2P5/1PPRQPPP/3R2K1 w - - acd 14; acn 309964326; acs -1; bm Nxf7; ce -13; id "ECM.1204"; pm Ne4; pv Ne4 Nxe5 Nxc5 Qxc5 Bxe5 Qc6 Qf1 d6 Bf4 d5 Bd3 Bc5 b4 Qxa4 bxc5 Qxf4 cxb6; ECMGCP.out ( 65): 2r2rk1/pp3qpp/8/3P1b2/3Q4/P1N1B3/5PKP/R2R4 b - - acd 13; acn 290453891; acs -1; bm Rxc3; id "ECM.1217"; pm Rc4; pv Rc4 Qxc4 Bh3+ Kxh3 Qf3+ Kh4 Qf6+ Kh5 Qg6+ Kh4 Qf6+; ECMGCP.out ( 69): 2r1r1k1/pp1nbpp1/4pn1p/q3NN1P/P1pP1B2/2P5/1PQ2PP1/R3R1K1 w - - acd 13; acn 203967028; acs -1; bm Nxg7; ce 15; id "ECM.1227"; pm Nxe7+; pv Nxe7+ Rxe7 Qd1 Qd5 Re3 a5 Qe2 Nb6 Bg3 Ree8 Bh4 Nfd7 Qg4 Ra8 Bg3; ECMGCP.out ( 70): 1r3rk1/6p1/p1pb1qPp/3p4/4nPR1/2N4Q/PPP4P/2K1BR2 b - - acd 13; acn 280946708; acs -1; bm Rxb2; ce 28; id "ECM.1229"; pm Be5; pv Be5 Qd3 Qf5 Rg2 Bxf4+ Kb1 Nxc3+ Bxc3 Qxd3 cxd3 Be3 Rxf8+ Kxf8 Be5 Re8 Bd6+ Kg8 Rc2 Rc8; ECMGCP.out ( 78): 3r1rk1/pbqn1pp1/1pp2n1p/2b1p1B1/P1B1P2N/2N4P/1PP1QPP1/3R1RK1 w - - acd 14; acn 423020265; acs -1; bm Rxd7; ce 36; id "ECM.1265"; pm Be3; pv Be3 Bxe3 fxe3 Nc5 Nf5 Kh7 Qf3 Rxd1 Rxd1 Bc8 b4 Na6 Bxa6 Bxa6 Rd6 Kg8; ECMGCP.out ( 83): 8/5p2/4p1k1/4P1p1/2rBRbK1/5P2/r4P2/7R b - - acd 18; acn 511110029; acs -1; bm Rxd4; ce -249; id "ECM.1273"; pm Bxe5; pv Bxe5 Rxe5 Rxd4+ Kg3 Rdd2 Rh2 Rac2 Kg4 Rd5 Rxd5 exd5 Rh1 f5+ Kg3 Kf6 Rh6+ Ke5 Rg6 d4 Rxg5 d3 Rg7; ECMGCP.out ( 90): 2r2rk1/p3p1bp/3qP1p1/1Q1p4/P4P2/3R4/1P4PP/2B2RK1 b - - acd 13; acn 134800580; acs -1; bm Rxc1; id "ECM.1294"; pm d4; pv d4 Re1 Rxc1 Rxc1 Qxf4 Rdd1 Be5 g3 Qf2+ Kh1 Qf3+ Kg1 Qf2+; ECMGCP.out ( 94): 1r2r1k1/1pqb2pp/p2bp1n1/2p3BQ/3pN3/1P1P2P1/P1P3BP/4RRK1 w - - acd 12; acn 102539629; acs -1; bm Bd8; id "ECM.1308"; pm Bc1; pv Bc1 Be7 Bg5 Bd6; ECMGCP.out ( 95): r3k2N/pppbq1pp/5n2/3Ppn2/2BP4/2P3bP/PP2Q1P1/RNB2K1R b q - acd 11; acn 55675086; acs -1; bm Bh2; ce 98; id "ECM.1314"; pm O-O-O; pv O-O-O Bg5 Rxh8 Nd2 h6 Be3 Rf8 Bf2 e4 Re1 e3 Bxg3 Nxg3+; ECMGCP.out (135): r1b2rk1/pp4bp/2p3p1/4q2n/NQPN1p1P/1P5n/P3PPB1/2BRRK2 b - - acd 12; acn 427316666; acs -1; bm f3; ce -53; id "ECM.1438"; pm Qc7; pv Qc7 Nf3 Bf5 Bb2 Bxb2 Nxb2 Rad8 Bxh3 Bxh3+ Kg1; ECMGCP.out (150): 1rb1r1k1/p1p1qppp/2pb4/8/2P3n1/4P1P1/PB2BP1P/R1QN1RK1 b - - acd 13; acn 216618258; acs -1; bm Nxh2; ce -66; id "ECM.1533"; pm Bf5; pv Bf5 Nc3 Be5 Na4 Rb4 Bxe5 Nxe5 Nb2 Reb8 Nd1 Nd3 Qc2 Rd8 Bxd3 Rxd3; ECMGCP.out (165): r2qrbk1/5ppp/pn1p4/np2P1P1/3p4/5N2/PPB2PP1/R1BQR1K1 w - - acd 13; acn 313768420; acs -1; bm Bxh7+; ce 61; id "ECM.1592"; pm e6; pv e6 fxe6 Nxd4 g6 Nxe6 Qc8 Nxf8 Rxe1+ Qxe1 Qxc2 Qe6+ Kg7 Qxd6 Rxf8 Qe5+ Kf7 Qf6+ Kg8 Qxb6; ECMGCP.out (176): r1b2r1k/ppppq1pp/2n1n3/6N1/2B2P2/4B3/PPP3PP/R2Q1RK1 w - - acd 12; acn 265118223; acs -1; bm Nxh7; ce 135; id "ECM.1612"; pm Qh5; pv Qh5 g6 Qh6 Qg7 Qxg7+ Kxg7 Nxe6+ dxe6 Rad1 b6 a3 h6 a4 Rd8 Rxd8 Nxd8 Kf2; ECMGCP.out (178): rn3rk1/pp1bppbp/1qp3p1/4P1N1/PP1PB3/2P1B3/4Q1PP/R4RK1 w - - acd 13; acn 321264763; acs -1; bm Nxh7; ce 229; id "ECM.1617"; pm e6; pv e6 Bxe6 Nxe6 fxe6 Qc4 Na6 Qxe6+ Kh8 Qxe7 Qc7 Qh4 Qd6 Bg5 Rae8 Rae1; ECMGCP.out (181): r2q3r/2pkb1p1/p2p1n2/4p1p1/Pp2P1P1/1QP5/1P1P2PP/RNB2RK1 b - - acd 13; acn 253449636; acs -1; bm Rxh2; ce 71; id "ECM.1621"; pm Qb8; pv Qb8 Qxb4 Qa7+ d4 d5 Qa5 exd4 Kh1 Rxh2+ Kxh2 Rh8+ Kg1 dxc3+ Rf2 Bc5 Be3 cxb2 Rxb2 Bxe3+ Kf1 dxe4; ECMGCP.out (182): 2rq1rk1/pp1bnpbp/4p1p1/3pP1N1/3P2Q1/2PB4/P4PPP/R1B1R1K1 w - - acd 15; acn 185481350; acs -1; bm Nxh7; ce 15; id "ECM.1622"; pm Bd2; pv Bd2 h6 Nf3 b5 Qh3 h5 Ng5 a6 Qf3 Qc7 Rac1 Bc6 Bf4 Nf5 h3;
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.