OpenChess

Sedat Canbaz wrote: Sun Jan 07, 2024 10:28 pm As usual,
Many thanks Mr. Homayoun, for all the news...

Best regards, Mr. Sedat

Finally, DualNNUE merged into the master branch of Stockfish!

Link to the specific commit: https://github.com/official-stockfish/S ... dfb06f52ba

General commit info:

Dual NNUE with L1-128 smallnet

Credit goes to @mstembera for:
- writing the code enabling dual NNUE:
#4898
- the idea of trying L1-128 trained exclusively on high simple eval
positions

The L1-128 smallnet is:
- epoch 399 of a single-stage training from scratch
- trained only on positions from filtered data with high material
difference
- defined by abs(simple_eval) > 1000

Training data can be found at:
https://robotmoon.com/nnue-training-data/

Local elo at 25k nodes per move of
L1-128 smallnet (nnue-only eval) vs. L1-128 trained on standard S1 data:
nn-epoch399.nnue : -318.1 +/- 2.1

Passed STC:
https://tests.stockfishchess.org/tests/ ... a1fcd49e3b
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 62432 W: 15875 L: 15521 D: 31036
Ptnml(0-2): 177, 7331, 15872, 7633, 203

Passed LTC:
https://tests.stockfishchess.org/tests/ ... cf40aaac6e
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 64830 W: 16118 L: 15738 D: 32974
Ptnml(0-2): 43, 7129, 17697, 7497, 49

closes https://github.com/official-stockfish/Stockfish/pulls

Bench: 1330050

Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com>

Author: Disservin
Date: Sun Jan 14 10:46:13 2024 +0100
Timestamp: 1705225573

Add ignoreRevsFile to CONTRIBUTING.md

closes https://github.com/official-stockfish/S ... /pull/4980

No functional change
https://abrok.eu/stockfish/
Note: Today we had 4 releases up to now, this one is the latest.

The latest stockfish is fire .
I like this one its giving GP problems though GP runs on December patch🥱

Author: Disservin
Date: Wed Jan 17 18:05:00 2024 +0100
Timestamp: 1705511100

Remove global TB variables from search.cpp

Follow up cleanup of #4968, removes the global variables from search and
instead uses a dedicated tb config struct.

closes https://github.com/official-stockfish/S ... /pull/4982

No functional change

https://abrok.eu/stockfish/

Author: Viren6
Date: Wed Jan 17 18:56:37 2024 +0100
Timestamp: 1705514197

Improve ttPv reduction

This patch allows a partial reduction decrease when a node is likely to
fail low, and increases the reduction decrease when a node has failed
high.

Passed STC:
https://tests.stockfishchess.org/tests/ ... f82b9722bc
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 157824 W: 40332 L: 39835 D: 77657 Elo +1.09
Ptnml(0-2): 543, 18617, 40098, 19108, 546

Passed LTC:
https://tests.stockfishchess.org/tests/ ... f82b97328a
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 57228 W: 14475 L: 14111 D: 28642 Elo +2.21
Ptnml(0-2): 34, 6278, 15633, 6628, 41

closes https://github.com/official-stockfish/S ... /pull/4994

Bench: 1364759
https://abrok.eu/stockfish/

Author: Muzhen Gaming
Date: Sun Jan 21 12:49:30 2024 +0100
Timestamp: 1705837770

VLTC search tune

Search parameters were tuned using 152k games at 180+1.8.

Passed VLTC:
https://tests.stockfishchess.org/tests/ ... f82b973a20
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 117338 W: 29244 L: 28848 D: 59246 Elo +1.17
Ptnml(0-2): 24, 12474, 33267, 12890, 14

Passed VVLTC:
https://tests.stockfishchess.org/tests/ ... f82b977982
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 28164 W: 7239 L: 6957 D: 13968 Elo +3.48
Ptnml(0-2): 3, 2651, 8490, 2937, 1

STC Elo estimate:
https://tests.stockfishchess.org/tests/ ... f82b9792a6
Elo: -0.53 ± 2.0 (95%) LOS: 30.4%
Total: 30000 W: 7688 L: 7734 D: 14578 Elo -0.53
Ptnml(0-2): 102, 3617, 7614, 3559, 108
nElo: -1.03 ± 3.9 (95%) PairsRatio: 0.99

closes https://github.com/official-stockfish/S ... /pull/5003

Bench: 1235377
https://abrok.eu/stockfish/

Author: Viren6
Date: Fri Jan 26 21:15:07 2024 +0100
Timestamp: 1706300107

Use ttPv in depth condition of singular extensions

This replaces the PvNode condition and tte Pv call previously with using
the precomputed ttPv, and also removes the multiplier of 2. This new
depth condition occurs with approximately equal frequency (47%) to the
old depth condition (measured when the other conditions in the if are
true), so non-linear scaling behaviour isn't expected.

Passed Non-Reg STC:
https://tests.stockfishchess.org/tests/ ... 0db026da27
LLR: 2.97 (-2.94,2.94) <-1.75,0.25>
Total: 243232 W: 62432 L: 62437 D: 118363 Elo -0.01
Ptnml(0-2): 910, 28937, 61900, 28986, 883

Passed Non-Reg LTC:
https://tests.stockfishchess.org/tests/ ... 0db026eea1
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 190596 W: 47666 L: 47618 D: 95312 Elo +0.09
Ptnml(0-2): 115, 21710, 51596, 21766, 111

closes https://github.com/official-stockfish/S ... /pull/5015

Bench: 1492957

https://abrok.eu/stockfish/

https://abrok.eu/stockfish/

Author: Muzhen Gaming
Date: Sat Feb 3 17:40:07 2024 +0100
Timestamp: 1706978407

Bench: 1478189
see source

Terminator wrote: Sat Feb 03, 2024 6:39 pm https://abrok.eu/stockfish/

Author: Muzhen Gaming
Date: Sat Feb 3 17:40:07 2024 +0100
Timestamp: 1706978407

Bench: 1478189
see source