FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
Active : 1 Machines / 30 Threads / 30.51 MNPS
Priority 0
Quanticade DarkNeutrino
pp
nnue.c: Change eval scale back
diff60.0+0.60
ELO    2.22 +- 2.06 (95%)
LLR    1.97 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 25618 W: 6106 L: 5942 D: 13570
PENTA  [11, 2880, 6865, 3040, 13]
Quanticade DarkNeutrino
master
25K node datagen.
diffN=25000
ELO    -0.02 +- 0.22 (95%)
GAMES  N: 6492886/30000000 W: 2278389 L: 2278805 D: 1935692
Finished
Quanticade DarkNeutrino
pp
Implement Pawn Pawn input set
diff60.0+0.60
ELO    -1.25 +- 8.85 (95%)
LLR    -0.14 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 1394 W: 326 L: 331 D: 737
PENTA  [2, 159, 379, 156, 1]
Quanticade DarkNeutrino
pp
Implement Pawn Pawn input set
diff10.0+0.10
ELO    -9.03 +- 5.07 (95%)
LLR    -2.32 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 5002 W: 1140 L: 1270 D: 2592
PENTA  [30, 654, 1248, 554, 15]
Quanticade DarkNeutrino
pp
Pawn pawn
diffN=5000
ELO    13.17 +- 5.83 (95%)
LLR    3.07 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 7680 W: 2708 L: 2417 D: 2555
PENTA  [283, 795, 1479, 914, 369]
Quanticade DarkNeutrino
D4D2F8C3BDC4446D
2 speedups both doing the same thing tho
diff4.0+0.04
ELO    2.56 +- 2.67 (95%)
LLR    1.50 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 17914 W: 4417 L: 4285 D: 9212
PENTA  [101, 1990, 4655, 2098, 113]
Quanticade DarkNeutrino
ttpv-reduction
search.c: Reduce more for tt_pv ahead of pruning
diff60.0+0.60
ELO    -0.70 +- 3.99 (95%)
LLR    -0.48 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6426 W: 1490 L: 1503 D: 3433
PENTA  [1, 710, 1803, 699, 0]
Quanticade DarkNeutrino
lmr-cutnode-ttmove
search.c: Reduce more if this node is cutnode and we dont have TT move
diff10.0+0.10
ELO    -2.64 +- 2.91 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 13306 W: 3064 L: 3165 D: 7077
PENTA  [20, 1592, 3529, 1493, 19]
Quanticade DarkNeutrino
multicut-corr
plenty stuff (search is depressing man)
diff10.0+0.10
ELO    0.18 +- 1.20 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 79832 W: 19016 L: 18975 D: 41841
PENTA  [123, 9357, 20951, 9326, 159]
Quanticade DarkNeutrino
tune
Tuned 4700 iters
smp diff20.0+0.20
ELO    1.07 +- 2.69 (95%)
LLR    0.28 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 13630 W: 3211 L: 3169 D: 7250
PENTA  [0, 1424, 3928, 1460, 3]
Quanticade DarkNeutrino
master
Source: Add and make use of removing lowest bit (#430)
diff60.0+0.60
ELO    90.78 +- 7.70 (95%)
GAMES  N: 1816/10000 W: 698 L: 234 D: 884
PENTA  [0, 50, 362, 478, 18]
Quanticade DarkNeutrino
simp-cutnode-lmr-ext
search.c: Simplify LMR extensions for cutnode
diff10.0+0.10
ELO    2.05 +- 2.58 (95%)
LLR    2.94 (-2.94, 2.94) [-3.00, 1.00]
GAMES  N: 17444 W: 4162 L: 4059 D: 9223
PENTA  [30, 2007, 4557, 2086, 42]
Quanticade DarkNeutrino
net58
net58 1024l1 otherwise same as net59 (yes weird to have earlier net)
diffN=25000
ELO    10.06 +- 4.65 (95%)
LLR    3.03 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8356 W: 2484 L: 2242 D: 3630
PENTA  [128, 956, 1812, 1110, 172]
Quanticade DarkNeutrino
nmp-improving
try what like 300 ?
diff10.0+0.10
ELO    -2.14 +- 2.70 (95%)
LLR    -2.29 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 15946 W: 3735 L: 3833 D: 8378
PENTA  [27, 1929, 4162, 1825, 30]
Quanticade DarkNeutrino
tuning
includes depths
smp diff20.0+0.20
TUNE   136 parameters
ITER   4,750 / 10,000
GAMES  19,002 / 40,000
Quanticade DarkNeutrino
net59
net59 50% more training
diff60.0+0.60
ELO    4.03 +- 2.77 (95%)
LLR    2.39 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 14036 W: 3389 L: 3226 D: 7421
PENTA  [10, 1520, 3787, 1699, 2]
Quanticade DarkNeutrino
net59
Fixed nodes test to even check
diffN=5000
ELO    2.56 +- 2.03 (95%)
LLR    3.03 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 63902 W: 21698 L: 21227 D: 20977
PENTA  [2719, 6809, 12565, 6998, 2860]
Quanticade DarkNeutrino
net59
net59 50% more training
diff10.0+0.10
ELO    1.73 +- 2.43 (95%)
LLR    0.95 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 20542 W: 5107 L: 5005 D: 10430
PENTA  [65, 2391, 5252, 2503, 60]
Quanticade DarkNeutrino
[Obsidian] main
kekw this I expect to be bad
diff10.0+0.10
ELO    -47.78 +- 6.77 (95%)
GAMES  N: 2810/10000 W: 539 L: 923 D: 1348
PENTA  [28, 523, 669, 175, 10]
Quanticade DarkNeutrino
tuning
Be good please
smp diff20.0+0.20
ELO    5.69 +- 3.26 (95%)
LLR    2.48 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 9158 W: 2161 L: 2011 D: 4986
PENTA  [2, 883, 2658, 1035, 1]
Quanticade DarkNeutrino
tuning
Tune duh
smp diff20.0+0.20
TUNE   127 parameters
ITER   7,230 / 10,000
GAMES  57,842 / 80,000
Quanticade DarkNeutrino
vnni
plz
diff2.0+0.02
ELO    -0.49 +- 1.35 (95%)
LLR    -2.30 (-2.25, 2.89) [0.00, 2.00]
GAMES  N: 72214 W: 18178 L: 18280 D: 35756
PENTA  [558, 8070, 18904, 8066, 509]
Quanticade DarkNeutrino
lmp-table
Source: Move LMP formula into a lookup table
diff4.0+0.04
ELO    3.13 +- 2.17 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 24858 W: 6139 L: 5915 D: 12804
PENTA  [75, 2693, 6711, 2833, 117]
Quanticade DarkNeutrino
master
Progtest LTC
diff60.0+0.60
ELO    69.54 +- 5.16 (95%)
GAMES  N: 4334/10000 W: 1500 L: 644 D: 2190
PENTA  [1, 198, 947, 986, 35]
Quanticade DarkNeutrino
master
Test against latest release STC
diff10.0+0.10
ELO    71.22 +- 3.66 (95%)
GAMES  N: 10022/10000 W: 3619 L: 1593 D: 4810
PENTA  [10, 500, 2147, 2162, 192]
Quanticade DarkNeutrino
tuning
Source: Tuned 3130 iters
smp diff20.0+0.20
ELO    1.28 +- 3.08 (95%)
LLR    0.33 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 10594 W: 2439 L: 2400 D: 5755
PENTA  [0, 1125, 3009, 1162, 1]
Quanticade DarkNeutrino
net58
1024L1 with 50% more SBs on both stages compared to master
crash smp diff16.0+0.16
ELO    -1.52 +- 3.62 (95%)
LLR    -0.93 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8000 W: 1864 L: 1899 D: 4237
PENTA  [3, 912, 2204, 879, 2]