Verdictimproved-policy-boundary
Live · 10s
SPRT · #202Failed
20,222games
Elo difference
-0.60± 2.76 at 95% confidence
LLR (-2.94, 2.94)
-2.97
Wins / losses / draws
4,963 / 4,998 / 10,261
Configuration
| Setting | Dev | Base |
|---|---|---|
| Engine | StockDory | StockDory |
| Source | https://github.com/TheBlackPlague/StockDory | https://github.com/TheBlackPlague/StockDory |
| Revision | 569303519c28a05b63797fca547e6a7743eedc01 | 2e4757a7d5c0f38b5b886852e1f415404913e3ea |
| Branch | improved-policy-boundary | master |
| Bench | 6209758 | 6099044 |
| Network | — | — |
| Options | Threads=1 Hash=16 | Threads=1 Hash=16 |
| Time control | 10.0+0.10 | 10.0+0.10 |
| Opening book | UHO_Lichess_4852_v1.epd | |
| Upload PGNs | FALSE | |
| Scaling | BASE 2000000 NPS | |
| Syzygy WDL | DISABLED | |
| Syzygy ADJ. | OPTIONAL | |
| Win ADJ. | movecount=3 score=400 | |
| Draw ADJ. | movenumber=40 movecount=8 score=10 | |
improved-policy-boundary vs master
Elo | -0.60 +- 2.76 (95%)
SPRT | 10.0+0.10s Threads=1 Hash=16MB
LLR | -2.97 (-2.94, 2.94) [0.00, 5.00]
Games | N: 20222 W: 4963 L: 4998 D: 10261
Penta | [230, 2465, 4751, 2440, 225]
LLR history
Results by contributor, CPU & ISA
Individual machine results
| # | User | Games | Penta | Pairs | Time | Crash |
|---|