Finished
WorldRecklessyet-another-dependencydiff8.0+0.08
LLR: 3.01 (-2.25, 2.89) [-2.75, 0.25]
Games: 23402 W: 5942 L: 5808 D: 11652
Ptnml(0-2): 50, 2702, 6091, 2780, 78
DanSamRecklesscutoff_cnt_to_cutoff_valuediff8.0+0.08
LLR: 2.90 (-2.25, 2.89) [0.00, 3.00]
Games: 69652 W: 17518 L: 17198 D: 34936
Ptnml(0-2): 152, 8026, 18152, 8342, 154
Use "weights" for cutoff count instead of incrementing 1
WorldRecklessyet-another-dependencydiff8.0+0.08
LLR: 2.94 (-2.25, 2.89) [-2.75, 0.25]
Games: 49280 W: 12442 L: 12358 D: 24480
Ptnml(0-2): 139, 5909, 12474, 5965, 153
WorldRecklessviri-corrhistdiff40.0+0.40
LLR: 1.37 (-2.25, 2.89) [0.00, 3.00]
Games: 66554 W: 16245 L: 16031 D: 34278
Ptnml(0-2): 16, 7487, 18064, 7687, 23
spec 50% tp
WorldRecklesslimit-fail-firm-weightdiff40.0+0.40
LLR: 2.98 (-2.25, 2.89) [0.00, 3.00]
Games: 25104 W: 6199 L: 5982 D: 12923
Ptnml(0-2): 11, 2719, 6875, 2936, 11
DanSamRecklesscutoff_cnt_next_cutnodediff8.0+0.08
LLR: -2.37 (-2.25, 2.89) [0.00, 3.00]
Games: 17384 W: 4258 L: 4357 D: 8769
Ptnml(0-2): 28, 2077, 4585, 1970, 32
Increase reduction in the cutoff count reduction if the next node is cutnode (FDS)
WorldRecklesslmr-tt-counterpartdiff8.0+0.08
LLR: 2.93 (-2.25, 2.89) [0.00, 3.00]
Games: 41654 W: 10389 L: 10125 D: 21140
Ptnml(0-2): 105, 4823, 10713, 5075, 111
DanSamRecklessprobcut_cutoff_cnt_incdiff8.0+0.08
LLR: -2.29 (-2.25, 2.89) [0.00, 3.00]
Games: 16884 W: 4098 L: 4195 D: 8591
Ptnml(0-2): 27, 2080, 4331, 1971, 33
Increment cutoff count in the probcut
WorldRecklessgeneralize-tt-lmr-2diff8.0+0.08
LLR: -1.93 (-2.25, 2.89) [-2.75, 0.25]
Games: 12288 W: 3035 L: 3175 D: 6078
Ptnml(0-2): 54, 1535, 3099, 1409, 47
WorldRecklesslimit-fail-firm-weightdiff8.0+0.08
LLR: 2.95 (-2.25, 2.89) [0.00, 3.00]
Games: 116574 W: 29222 L: 28795 D: 58557
Ptnml(0-2): 253, 13659, 30051, 14056, 268
8/9
WorldRecklessgeneralize-tt-lmrdiff8.0+0.08
LLR: -2.43 (-2.25, 2.89) [-2.75, 0.25]
Games: 14714 W: 3577 L: 3746 D: 7391
Ptnml(0-2): 28, 1846, 3779, 1675, 29
WorldRecklesslimit-fail-firm-weight-2diff8.0+0.08
LLR: 0.43 (-2.25, 2.89) [0.00, 3.00]
Games: 23966 W: 6024 L: 5946 D: 11996
Ptnml(0-2): 67, 2789, 6190, 2873, 64
6/7
ProtonRecklessps_islegal108diff40.0+0.40
LLR: 0.80 (-2.25, 2.89) [-2.75, 0.25]
Games: 5620 W: 1372 L: 1337 D: 2911
Ptnml(0-2): 5, 620, 1523, 659, 3
Simplify is_legal.
WorldRecklessdatagen-9diffN=5000
Generated 30000040/30000000 Games
Elo: 0.08 +- 0.09 (95%) [N=30000000]
Games: 30000040 W: 8495426 L: 8488573 D: 13016041
[SELF-PLAY-01]
ProtonRecklessps_islegal108diff8.0+0.08
LLR: 2.90 (-2.25, 2.89) [-2.75, 0.25]
Games: 36782 W: 9167 L: 9068 D: 18547
Ptnml(0-2): 78, 3977, 10202, 4036, 98
Simplify is_legal.
DanSamRecklesscutoff_hist_3diff8.0+0.08
LLR: -2.34 (-2.25, 2.89) [0.00, 3.00]
Games: 15878 W: 3963 L: 4067 D: 7848
Ptnml(0-2): 55, 1930, 4072, 1828, 54
try 1:1 implementation of the idea (https://tests.stockfishchess.org/tests/view/6971d6b712ee1f6231b97369)
DanSamRecklesscutnode_corr_2diff8.0+0.08
LLR: -2.29 (-2.25, 2.89) [0.00, 3.00]
Games: 6158 W: 1453 L: 1568 D: 3137
Ptnml(0-2): 14, 727, 1704, 628, 6
ProtonRecklessps_pinners100diff8.0+0.08
LLR: -0.84 (-2.25, 2.89) [0.00, 3.00]
Games: 35696 W: 8866 L: 8838 D: 17992
Ptnml(0-2): 85, 3952, 9751, 3970, 90
I break stuff.
DanSamRecklesscutnode_corr_2diff8.0+0.08
LLR: -2.43 (-2.25, 2.89) [0.00, 3.00]
Games: 20142 W: 4954 L: 5050 D: 10138
Ptnml(0-2): 55, 2296, 5455, 2220, 45
3171793
DanSamRecklesscutnode_corr_2diff8.0+0.08
LLR: -2.26 (-2.25, 2.89) [0.00, 3.00]
Games: 12086 W: 2993 L: 3100 D: 5993
Ptnml(0-2): 29, 1509, 3074, 1402, 29
PeregrRecklessqslmp-ttm2diff8.0+0.08
LLR: -2.44 (-2.25, 2.89) [0.00, 3.00]
Games: 13344 W: 3294 L: 3409 D: 6641
Ptnml(0-2): 27, 1673, 3397, 1538, 37
PeregrRecklesspslmp-ttmdiff8.0+0.08
LLR: -2.38 (-2.25, 2.89) [0.00, 3.00]
Games: 18068 W: 4451 L: 4552 D: 9065
Ptnml(0-2): 51, 2200, 4631, 2103, 49
qslmp*
DanSamRecklesscutnode_corrdiff8.0+0.08
LLR: -2.26 (-2.25, 2.89) [0.00, 3.00]
Games: 26810 W: 6679 L: 6753 D: 13378
Ptnml(0-2): 69, 3209, 6944, 3093, 90
different bonus formula for cutnode corrhist + use it to adjust nmp threshold
PeregrRecklessqslmp-quietdiff8.0+0.08
LLR: -2.25 (-2.25, 2.89) [0.00, 3.00]
Games: 17776 W: 4402 L: 4495 D: 8879
Ptnml(0-2): 37, 2152, 4611, 2043, 45
WorldRecklessno-longer-relevantdiff8.0+0.08
LLR: 0.72 (-2.25, 2.89) [-2.75, 0.25]
Games: 103176 W: 25529 L: 25669 D: 51978
Ptnml(0-2): 260, 11284, 28630, 11164, 250
check if it's relevant since we search quiets in qsearch when tt move is quiet — maybe try with ttm-upper-qs later or smth