| Finished | ||||||
|---|---|---|---|---|---|---|
| Kovax | Leela-dag-preview | debl1M-hpol-grill9-25k | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 21012 W: 4811 L: 4614 D: 11587 Ptnml(0-2): 0, 2074, 6166, 2261, 5 | Grill vs k2hybrid |
| Kovax | Leela-dag-preview | debl1M-hpol-grill9-25k | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 3282 W: 817 L: 647 D: 1818 Ptnml(0-2): 1, 286, 896, 458, 0 | Grill target vs baseline |
| Menkib | Leela-dag-preview | monitor_wait | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [-3.00, 0.00] Games: 24932 W: 6272 L: 6167 D: 12493 Ptnml(0-2): 2, 2456, 7450, 2551, 7 | Implement support for high power state selection. |
| Menkib | Leela-dag-preview | cache_concurrency_refactoring | diff | 8.0+0.08 | LLR: 2.96 (-2.94, 2.94) [-3.00, 0.00] Games: 20062 W: 5030 L: 4915 D: 10117 Ptnml(0-2): 1, 1953, 6009, 2066, 2 | Avoid race between ucinewgame and search stopping. |
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 20.0+0.20 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 53004 W: 13980 L: 13721 D: 25303 Ptnml(0-2): 24, 5216, 15767, 5467, 28 | Calibration Elo test Dev 3305 vs Base 3365 |
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 80.0+0.80 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 30182 W: 7763 L: 7551 D: 14868 Ptnml(0-2): 7, 2918, 9026, 3136, 4 | Calibration Elo test Dev 3320 vs Base 3260 |
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 80.0+0.80 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 36670 W: 9487 L: 9265 D: 17918 Ptnml(0-2): 7, 3479, 11144, 3695, 10 | Calibration Elo test Dev 3320 vs Base 3380 |
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 40.0+0.40 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 17374 W: 4594 L: 4407 D: 8373 Ptnml(0-2): 3, 1648, 5199, 1833, 4 | Calibration Elo test Dev 3320 vs Base 3350 |
| Menkib | Leela-dag-preview | no-task-workers | diff | 8.0+0.08 | LLR: 2.96 (-2.94, 2.94) [-3.00, 0.00] Games: 29400 W: 7375 L: 7275 D: 14750 Ptnml(0-2): 24, 3018, 8513, 3124, 21 | Optimize new tasks when task workers are disabled |
| Menkib | Leela-dag-preview | fix-bound-update-thread-reordering | diff | 8.0+0.08 | LLR: 2.96 (-2.94, 2.94) [-3.00, 0.00] Games: 53846 W: 13418 L: 13369 D: 27059 Ptnml(0-2): 7, 5294, 16274, 5339, 9 | Increase error tolerances for value calculation |
| Menkib | Leela-dag-preview | tcec-season-30-task-workers | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [-3.00, 0.00] Games: 59990 W: 14852 L: 14815 D: 30323 Ptnml(0-2): 8, 5896, 18150, 5933, 8 | Add missing fields to node to process debug output |
| Menkib | Leela-dag-preview | fix-bound-update-thread-reordering-pathless-repetition | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 14128 W: 3585 L: 3407 D: 7136 Ptnml(0-2): 0, 1292, 4305, 1464, 3 | Increase error tolerances for value calculation |
| Menkib | Leela-dag-preview | tcec-season-30-tt-owns-low-node | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [-3.00, 0.00] Games: 40750 W: 10248 L: 10174 D: 20328 Ptnml(0-2): 9, 4021, 12237, 4103, 5 | Store shared pointer directly in cache |
| Menkib | Leela-dag-preview | tcec-season-30-repetition-update | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [-3.00, 0.00] Games: 14970 W: 3775 L: 3651 D: 7544 Ptnml(0-2): 4, 1426, 4501, 1550, 4 | Trace scope contested spin mutex and variable spin limit. |
| Menkib | Leela-dag-preview | tcec-season-30-solid-edges | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [-3.00, 0.00] Games: 29888 W: 7463 L: 7372 D: 15053 Ptnml(0-2): 3, 2677, 9492, 2770, 2 | Avoid losing tree in single child release |
| Kovax | Leela-dag-preview | policy-blend-gpu | diff | 10.0+0.10 | Elo: 20.21 +- 3.07 (95%) [N=10000] Games: 10000 W: 2542 L: 1961 D: 5497 Ptnml(0-2): 1, 745, 2929, 1322, 3 | no early stopping |
| Kovax | Leela-dag-preview | policy-blend-gpu | diff | 10.0+0.10 | LLR: 2.94 (-2.94, 2.94) [0.00, 3.00] Games: 2082 W: 568 L: 408 D: 1106 Ptnml(0-2): 0, 137, 609, 293, 2 | testing policy blending on gpu with the params of cpu blending |
| Menkib | Leela-dag-preview | tcec-season-30-solid-edges | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [-3.00, 0.00] Games: 1234 W: 409 L: 225 D: 600 Ptnml(0-2): 0, 48, 337, 232, 0 | Use waitable atomic for task worker state |
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 1800.0+3.00 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 23838 W: 5924 L: 5745 D: 12169 Ptnml(0-2): 0, 1846, 8049, 2023, 1 | Calibration Elo test for LCZeroCPU on TCEC. (100 Elo) |
| Kovax | Leela-dag-preview | debl1M-k2hyb-100k | diff | 10.0+0.10 | LLR: 2.94 (-2.94, 2.94) [0.00, 3.00] Games: 9740 W: 2267 L: 2088 D: 5385 Ptnml(0-2): 0, 971, 2753, 1142, 4 | k2hyb recheck, as this net played vs 100k instead of 1M |
| Kovax | Leela-dag-preview | policy-blend | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 8412 W: 1970 L: 1798 D: 4644 Ptnml(0-2): 1, 775, 2483, 945, 2 | Optimistic blend vs Master post softmax. |
| Kovax | Leela-dag-preview | master | diff | N=1000 | Elo: 11.91 +- 1.76 (95%) [N=40000] Games: 40014 W: 10593 L: 9222 D: 20199 Ptnml(0-2): 181, 3889, 10566, 5120, 251 | check how much PST and FPU is shift alone gains with the sharp target corpus. |
| Menkib | Leela-dag-preview | t3d-kd2-03007500.pb.gz | diff | 180.0+0.30 | LLR: 2.94 (-2.94, 2.94) [0.00, 3.00] Games: 2076 W: 605 L: 444 D: 1027 Ptnml(0-2): 0, 139, 600, 298, 1 | t3d vs BT4 |
| Menkib | Leela-dag-preview | t3d-kd2-03007500.pb.gz * | diff | 180.0+0.30 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 2184 W: 666 L: 487 D: 1031 Ptnml(0-2): 10, 137, 610, 334, 1 | t3d vs BT4 |
| Johnsp | Leela-dag-preview | t3d-kd2-03477500 | diff | 40.0+0.40 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 1698 W: 451 L: 297 D: 950 Ptnml(0-2): 0, 89, 517, 243, 0 | LTC - Verification of T3d-kd2 without uncertainty |