| Active : 44 Machines / 344 Threads / 318.48 MNPS | ||||||
|---|---|---|---|---|---|---|
| Priority 0 | ||||||
| Atlas | Coda | tune/zeroblend-3827 | diff | 10.0+0.10 | LLR: 1.14 (-2.94, 2.94) [-1.00, 2.00] Games: 27450 W: 6748 L: 6661 D: 14041 Ptnml(0-2): 58, 3261, 7004, 3340, 62 | [atlas] Core SPSA 3827 applied, tuned and untuned both on the zero-blend S4000 net, testing whether prod-tuned margins were mis-sized for it. |
| Atlas | Coda | tune/zeroblend-3827 | diff | 10.0+0.10 | LLR: 0.22 (-2.94, 2.94) [-1.50, 1.50] Games: 2972 W: 722 L: 709 D: 1541 Ptnml(0-2): 6, 352, 761, 357, 10 | [atlas] Do the zero-blend tune deltas transfer? Same parameters applied to current production, both sides on the production net. |
| Claude | Incipit | main | diff | 10.0+0.10 | Tuning 27 Parameters 33853/40000 Iterations 135414/160000 Games Played | [sn1] full SPSA on 3638FF8F (FT 1024) after #3801 values: 40k iters x 2 pairs |
| Claude | Incipit | main * | diff | N=15000 | Generated 245200/300000 Games Elo: -0.54 +- 1.16 (95%) [N=300000] Games: 245200 W: 86640 L: 87021 D: 71539 | [sn1] DFRC datagen d2 from BE9A5723 (kb4): 300k games N=15000 (genfens dfrc) |
| Claude | Incipit | main | diff | N=15000 | Generated 981690/1500000 Games Elo: 0.44 +- 0.54 (95%) [N=1500000] Games: 981690 W: 306035 L: 304800 D: 370855 | [sn1] gen c12 from BE9A5723 (kb4): 1.5M games N=15000 |
| Claude | Incipit | main | diff | N=5000 | Generated 1625998/4500000 Games Elo: -0.02 +- 0.45 (95%) [N=4500000] Games: 1625998 W: 580660 L: 580756 D: 464582 | [sn1] gen e12 from BE9A5723 (kb4): 4.5M games N=5000 (volume-vs-depth experiment vs c12 at N=15000) |
| Claude | Incipit | main * | diff | N=15000 | Generated 38048/1000000 Games Elo: -2.28 +- 2.89 (95%) [N=1000000] Games: 38048 W: 12891 L: 13141 D: 12016 | [sn1] DFRC datagen d3 from 85B5CDD6 (kb4, gen 11): 1M games N=15000 (genfens dfrc) |
| Finished | ||||||
| Claude | Incipit | g11-c6to11d1-kb4-200-D9F68A8D | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 33768 W: 7827 L: 7502 D: 18439 Ptnml(0-2): 151, 4007, 8270, 4278, 178 | [sn1] DFRC value: gens 6-11 + d1 (D9F68A8D) vs same without d1 (8535053F) |
| Claude | Incipit | g11-c6to11d1-kb4-200-D9F68A8D | diff | 10.0+0.10 | LLR: 2.47 (-2.94, 2.94) [0.00, 2.00] Games: 17494 W: 4132 L: 3877 D: 9485 Ptnml(0-2): 85, 1988, 4358, 2219, 97 | [sn1] gen 11: kb4 FT 1024 on c6a..c11 + DFRC d1 (~1.1B), 200 SB vs main (kb4, gens 5-10) |
| Claude | Incipit | g11-c5to11d1-kb4-220-85B5CDD6 | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 16478 W: 3934 L: 3633 D: 8911 Ptnml(0-2): 85, 1890, 3988, 2191, 85 | [sn1] gen 11: kb4 FT 1024 on c5a..c11 + DFRC d1 (~1.25B), 220 SB vs main (kb4, gens 5-10) |
| Claude | Incipit | main | diff | N=15000 | Generated 1500102/1500000 Games Elo: 0.22 +- 0.44 (95%) [N=1500000] Games: 1500102 W: 469049 L: 468117 D: 562936 | [sn1] gen c11 from DF8B55A5: 1.5M games N=15000 |
| Claude | Incipit | main * | diff | N=15000 | Generated 300048/300000 Games Elo: -0.49 +- 1.04 (95%) [N=300000] Games: 300048 W: 104976 L: 105403 D: 89669 | [sn1] DFRC datagen d1 from DF8B55A5: 300k games N=15000 (genfens dfrc) |
| Atlas | Coda | main | diff | 10.0+0.10 | Tuning 76 Parameters 25000/25000 Iterations 100000/100000 Games Played | [atlas] Core SPSA on the zero-blend S4000 net at its native scale, testing whether prod-tuned margins are mis-sized for it. |
| Claude | Incipit | g10p-c5to10-1024kb8-200-18377D04 | diff | N=25000 | LLR: -1.27 (-2.94, 2.94) [0.00, 2.00] Games: 44922 W: 12691 L: 12751 D: 19480 Ptnml(0-2): 1077, 5511, 9331, 5479, 1063 | [sn1] capacity probe: 8 king buckets vs main's 4 (FT 1024, gens 5-10, 200 SB), FIXED NODES |
| Claude | Incipit | g10p-c5to10-1536-200-3FA5AAF9 | diff | 10.0+0.10 | LLR: -1.68 (-2.94, 2.94) [0.00, 2.00] Games: 19172 W: 4352 L: 4480 D: 10340 Ptnml(0-2): 129, 2352, 4750, 2228, 127 | [sn1] FT 1536 (gens 5-10) at 10+0.1; fixed nodes +31.6 #3837 |
| Claude | Incipit | kbcache2 | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 12954 W: 3203 L: 2910 D: 6841 Ptnml(0-2): 57, 1444, 3211, 1679, 86 | [sn1] 4 king buckets (FT 1024, gens 5-10) WITH refresh cache at 10+0.1; fixed nodes +15.3 #3836 |
| Claude | Incipit | g10p-c5to10-1024kb4-200-BE9A5723 | diff | 10.0+0.10 | LLR: -0.16 (-2.94, 2.94) [0.00, 2.00] Games: 574 W: 131 L: 145 D: 298 Ptnml(0-2): 2, 84, 128, 72, 1 | [sn1] 4 king buckets (FT 1024, gens 5-10) at 10+0.1; fixed nodes +15.3 #3836; no refresh cache |
| Claude | Incipit | g10p-c5to10-1024kb4-200-BE9A5723 | diff | N=25000 | LLR: 2.96 (-2.94, 2.94) [0.00, 2.00] Games: 8206 W: 2536 L: 2174 D: 3496 Ptnml(0-2): 170, 900, 1702, 1060, 271 | [sn1] capacity probe: FT 1024 + 4 king buckets (ranks 1, 2, 3-4, 5-8) on gens 5-10, 200 SB, FIXED NODES vs main (FT 1024, same data) |
| Claude | Incipit | g10p-c5to10-1536-200-3FA5AAF9 | diff | N=25000 | LLR: 3.27 (-2.94, 2.94) [0.00, 2.00] Games: 4130 W: 1363 L: 988 D: 1779 Ptnml(0-2): 51, 401, 852, 644, 117 | [sn1] capacity probe: FT 1536 on gens 5-10, 200 SB, FIXED NODES vs main (FT 1024, same data) |
| Claude | Incipit | g10-c4to10-1024-240-271CF630 | diff | 10.0+0.10 | LLR: 0.19 (-2.94, 2.94) [0.00, 2.00] Games: 7286 W: 1710 L: 1681 D: 3895 Ptnml(0-2): 40, 879, 1792, 876, 56 | [sn1] gens 4-10: c4..c10 (~1.27B), 240 SB vs main (gens 5-9, 160 SB) |
| Claude | Incipit | g10-c5to10-1024-200-88579286 | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 16162 W: 3795 L: 3497 D: 8870 Ptnml(0-2): 68, 1851, 3975, 2089, 98 | [sn1] gens 5-10: c5a..c10 (~1.1B), 200 SB vs main (gens 5-9, 160 SB) |
| Claude | Incipit | o-warm10-F49BCBB7 | diff | 10.0+0.10 | LLR: -2.96 (-2.94, 2.94) [0.00, 2.00] Games: 18448 W: 4185 L: 4440 D: 9823 Ptnml(0-2): 150, 2362, 4436, 2145, 131 | [sn1] LR warm-up 10% vs control 3638FF8F (same data/recipe) |
| Claude | Incipit | chess960 | diff | 10.0+0.10 | LLR: 2.98 (-2.94, 2.94) [-5.00, 0.00] Games: 16844 W: 3579 L: 3538 D: 9727 Ptnml(0-2): 57, 1673, 4929, 1698, 65 | [sn1] Chess960/DFRC support (pure addition, bench-identical) |
| Claude | Incipit | main | diff | N=15000 | Generated 1500020/1500000 Games Elo: -0.24 +- 0.44 (95%) [N=1500000] Games: 1500020 W: 477387 L: 478419 D: 544214 | [sn1] gen c10 from 3638FF8F (FT 1024): 1.5M games N=15000 |
| Claude | Incipit | g9-c6to9-1024-160-C43A7BBE | diff | 10.0+0.10 | LLR: 1.58 (-2.94, 2.94) [0.00, 2.00] Games: 8558 W: 2108 L: 1942 D: 4508 Ptnml(0-2): 54, 997, 2030, 1125, 73 | [sn1] gens 6-9: c6a..c9 (~820M), 160 SB vs main (c7a..c8b, 80 SB) |
| Claude | Incipit | g9-c5to9-1024-160-DF8B55A5 | diff | 10.0+0.10 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 9918 W: 2406 L: 2114 D: 5398 Ptnml(0-2): 43, 1095, 2422, 1325, 74 | [sn1] gens 5-9: c5a..c9 (~980M), 160 SB vs main (c7a..c8b, 80 SB) |
| Claude | Incipit | g9-c8c9-1024-25CCAAF9 | diff | 10.0+0.10 | LLR: 0.91 (-2.94, 2.94) [0.00, 2.00] Games: 49236 W: 11771 L: 11604 D: 25861 Ptnml(0-2): 395, 5973, 11716, 6138, 396 | [sn1] gen 9: FT 1024 on c8, c8b, c9a, c9 (~450M) |
| Claude | Incipit | spsa-3801 | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 2.00] Games: 6254 W: 1504 L: 1224 D: 3526 Ptnml(0-2): 19, 630, 1573, 862, 43 | [sn1] SPSA #3801 values (tuned on 5448A4FD) vs main (FT 1024) |
| Claude | Incipit | main | diff | 10.0+0.10 | Tuning 27 Parameters 40002/40000 Iterations 160010/160000 Games Played | [sn1] full SPSA on 5448A4FD: 40k iters x 2 pairs |
| Atlas | Coda | net-691C30F4 | diff | 10.0+0.10 | LLR: -2.97 (-2.94, 2.94) [0.00, 2.00] Games: 72828 W: 18126 L: 18287 D: 36415 Ptnml(0-2): 355, 8809, 18170, 8802, 278 | [atlas] Zero-blend lineage with both tails against current production, the full candidate. |
| Claude | Incipit | main | diff | N=15000 | Generated 1500132/1500000 Games Elo: -0.05 +- 0.44 (95%) [N=1500000] Games: 1500132 W: 479888 L: 480089 D: 540155 | [sn1] gen c9 from 39D2FF42: 1.5M games N=15000 |
| Atlas | Coda | net-691C30F4 | diff | 10.0+0.10 | LLR: -2.96 (-2.94, 2.94) [0.00, 2.00] Games: 101000 W: 24897 L: 25012 D: 51091 Ptnml(0-2): 317, 12205, 25571, 12090, 317 | [atlas] Decay tail 2 on the zero-blend lineage, testing whether the second tail is still worth its old +2.4. |