VerdictTests
Live · 10s
1 active 0 awaiting approval 18 machines online 240 threads 466.1 MNPS Estimated Time Remaining ~21h 11m
| Workload | Status | Engine / TC | Result | Games / W–L–D / Pentanomial | Notes | Compare revisions |
|---|---|---|---|---|---|---|
| Active workloads 1Priority 0 | ||||||
| master | Active | StockDory 120.0+1.20 | LLR: 0.10 (-2.94, 2.94) [0.00, 5.00] Elo: 4.34 +- 17.17 (95%) | Games: 320 W: 83 L: 79 D: 158 Ptnml(0-2): 1, 26, 102, 30, 1 | ⚒️ FIX: Prevent Maximum Search Depth Overflow | |
| Finished workloadsMost recently updated | ||||||
| correction-history | Passed | StockDory 120.0+1.20 | LLR: 2.97 (-2.94, 2.94) [0.00, 5.00] Elo: 20.97 +- 8.15 (95%) | Games: 1924 W: 474 L: 358 D: 1092 Ptnml(0-2): 5, 180, 487, 274, 16 | Merge branch 'master' into correction-history | |
| correction-history | Passed | StockDory 60.0+0.60 | LLR: 2.95 (-2.94, 2.94) [0.00, 5.00] Elo: 20.37 +- 8.14 (95%) | Games: 1998 W: 521 L: 404 D: 1073 Ptnml(0-2): 5, 196, 494, 285, 19 | chore: try deferring neural network evaluation whenever possible | |
| correction-history | Passed | StockDory 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 5.00] Elo: 4.83 +- 3.61 (95%) | Games: 12808 W: 3231 L: 3053 D: 6524 Ptnml(0-2): 161, 1520, 2913, 1600, 210 | chore: try deferring neural network evaluation whenever possible | |
| correction-history | Passed | StockDory 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Elo: 1.40 +- 2.41 (95%) | Games: 25892 W: 6626 L: 6522 D: 12744 Ptnml(0-2): 266, 3044, 6255, 3082, 299 | try gaining some speedup elo back | |
| better-tt-replacement | Failed | StockDory 10.0+0.10 | LLR: -2.95 (-2.94, 2.94) [0.00, 5.00] Elo: 0.58 +- 1.79 (95%) | Games: 47862 W: 11458 L: 11378 D: 25026 Ptnml(0-2): 505, 5800, 11255, 5852, 519 | feat(tt): implement a more efficient replacement scheme with age logic | |
| better-tactical-handling-no-check | Passed | StockDory 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Elo: 0.19 +- 1.52 (95%) | Games: 66942 W: 16022 L: 15985 D: 34935 Ptnml(0-2): 725, 8169, 15655, 8188, 734 | Merge branch 'master' into better-tactical-handling-no-check | |
| tt-cluster | Failed | StockDory 10.0+0.10 | LLR: -2.97 (-2.94, 2.94) [0.00, 5.00] Elo: -3.32 +- 4.21 (95%) | Games: 8696 W: 2025 L: 2108 D: 4563 Ptnml(0-2): 105, 1079, 2053, 1016, 95 | fix(tt): have replacement logic fully in search & try a move replacement scheme | |
| continuation-history-lmr | Failed | StockDory 10.0+0.10 | LLR: -2.95 (-2.94, 2.94) [0.00, 5.00] Elo: 0.81 +- 1.53 (95%) | Games: 65220 W: 15612 L: 15460 D: 34148 Ptnml(0-2): 743, 7798, 15320, 8062, 687 | feat(lmr): increase or reduce reduction for quiets based on continuation history | |
| tt-cluster | Failed | StockDory 10.0+0.10 | LLR: -3.04 (-2.94, 2.94) [0.00, 5.00] Elo: -4.78 +- 4.78 (95%) | Games: 6828 W: 1595 L: 1689 D: 3544 Ptnml(0-2): 80, 882, 1577, 802, 73 | fix(tt): use age to fix clustering | |
| tt-cluster | Failed | StockDory 10.0+0.10 | LLR: -2.98 (-2.94, 2.94) [0.00, 5.00] Elo: -17.16 +- 8.36 (95%) | Games: 2270 W: 486 L: 598 D: 1186 Ptnml(0-2): 39, 307, 538, 229, 22 | feat(tt): implement clustering | |
| mantaray-v5 | Passed | StockDory 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [-3.00, 1.00] Elo: 5.21 +- 4.14 (95%) | Games: 8800 W: 2181 L: 2049 D: 4570 Ptnml(0-2): 84, 1010, 2101, 1100, 105 | fix: update MantaRay v5 for ARM inference throughput (3 / 3 - positive) | |
| mantaray-v5 | Passed | StockDory 10.0+0.10 | LLR: 3.04 (-2.94, 2.94) [-3.00, 1.00] Elo: 3.54 +- 3.40 (95%) | Games: 12464 W: 3056 L: 2929 D: 6479 Ptnml(0-2): 105, 1421, 3087, 1480, 139 | fix: update MantaRay v5 for ARM inference throughput (2 / 3 - possibly false positive) | |
| mantaray-v5 | Failed | StockDory 10.0+0.10 | LLR: -2.95 (-2.94, 2.94) [-3.00, 1.00] Elo: -2.84 +- 2.59 (95%) | Games: 22106 W: 5226 L: 5407 D: 11473 Ptnml(0-2): 248, 2663, 5384, 2538, 220 | chore: update MantaRay v5 (1 / 3 - marked false-negative) | |
| continuation-history | Passed | StockDory 10.0+0.10 | LLR: 2.97 (-2.94, 2.94) [0.00, 5.00] Elo: 13.47 +- 6.67 (95%) | Games: 3432 W: 880 L: 747 D: 1805 Ptnml(0-2): 28, 375, 790, 482, 41 | feat(history): implement counter-move history - 2T | |
| continuation-history | Passed | StockDory 60.0+0.60 | LLR: 2.97 (-2.94, 2.94) [0.00, 5.00] Elo: 28.38 +- 9.50 (95%) | Games: 1362 W: 349 L: 238 D: 775 Ptnml(0-2): 0, 120, 340, 211, 10 | feat(history): implement counter-move history | |
| continuation-history | Passed | StockDory 10.0+0.10 | LLR: 2.99 (-2.94, 2.94) [0.00, 5.00] Elo: 21.13 +- 8.63 (95%) | Games: 2190 W: 603 L: 470 D: 1117 Ptnml(0-2): 17, 238, 468, 339, 33 | feat(history): implement counter-move history | |
| continuation-history | Passed | StockDory N=10000 | Elo: -0.00 +- 0.00 (95%) [N=20000] | Games: 20284 W: 6893 L: 6893 D: 6498 Ptnml(0-2): 0, 0, 10142, 0, 0 | fix(policy): avoid an anchor and use int32 scores for policy | |
| mantaray-v5 | Passed | StockDory N=50000 | Elo: -0.00 +- 0.00 (95%) [N=50000] | Games: 50012 W: 14477 L: 14477 D: 21058 Ptnml(0-2): 0, 0, 25006, 0, 0 | fix: update MantaRay v5 for ARM inference throughput | |
| mantaray-v4 | Passed | StockDory 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Elo: -0.21 +- 1.03 (95%) | Games: 141462 W: 33790 L: 33875 D: 73797 Ptnml(0-2): 1506, 16774, 34274, 16653, 1524 | chore: update MantaRay v4 dependency | |
| mantaray-v4 | Passed | StockDory N=10000 | Elo: -0.00 +- 0.00 (95%) [N=10000] | Games: 10192 W: 3463 L: 3463 D: 3266 Ptnml(0-2): 0, 0, 5096, 0, 0 | chore: update MantaRay v4 dependency | |
| mantaray-v4 | Failed | StockDory 10.0+0.10 | LLR: -2.95 (-2.94, 2.94) [-3.00, 1.00] Elo: -1.22 +- 1.39 (95%) | Games: 77164 W: 18274 L: 18545 D: 40345 Ptnml(0-2): 831, 9276, 18573, 9137, 765 | feat: migrate to MantaRay v4 | |
| mantaray-v4 | Passed | StockDory N=10000 | Elo: -0.00 +- 0.00 (95%) [N=5000] | Games: 5124 W: 1720 L: 1720 D: 1684 Ptnml(0-2): 0, 0, 2562, 0, 0 | feat: migrate to MantaRay v4 | |
| tune-135 | Failed | StockDory 10.0+0.10 | LLR: -3.01 (-2.94, 2.94) [0.00, 5.00] Elo: -1.20 +- 3.13 (95%) | Games: 15938 W: 3780 L: 3835 D: 8323 Ptnml(0-2): 171, 2015, 3666, 1932, 185 | chore: try tuned parameters | |
| tm-stability-bm | Stopped | StockDory 120.0+1.20 | LLR: 1.83 (-2.94, 2.94) [0.00, 5.00] Elo: 1.84 +- 1.73 (95%) | Games: 39938 W: 8656 L: 8445 D: 22837 Ptnml(0-2): 119, 4581, 10366, 4776, 127 | feat(tm): add best move stability | |
| master | Finished | StockDory 10.0+0.10 | Tuning 5 Parameters 15000/15000 Iterations | 240004/240000 Games Played | — | |