Cold-start re-baseline after the DESIGN.md 38.10/38.11 objective change. Single worker (avoids homemaker-py-b8g), scored by the shipped scorer from the programme directory. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MJ84Feep79Hhm3E4zZJmnB
114 lines
8 KiB
Text
114 lines
8 KiB
Text
15s [ 200 evals] best 2.78368e-25 (fails 78) via seed
|
|
24s [ 280 evals] best 2.81966e-25 (fails 78) via place_missing noop
|
|
32s [ 840 evals] best 2.83081e-25 (fails 78) via level_fix noop
|
|
49s [ 1240 evals] best 2.85681e-25 (fails 78) via undivide 1/rlrll
|
|
66s [ 1880 evals] best 2.86707e-25 (fails 78) via place_missing noop
|
|
66s [ 1960 evals] best 4.17745e-25 (fails 77) via crossover rlll<->llr
|
|
74s [ 2280 evals] best 1.76161e-24 (fails 75) via rotate 0/ll
|
|
90s [ 3080 evals] best 4.67378e-24 (fails 74) via undivide 0/rllll
|
|
118s [ 4120 evals] best 1.46076e-23 (fails 72) via level_retype 1/lrll<->0/lrlrr
|
|
144s [ 5160 evals] best 1.36798e-22 (fails 69) via place_missing n -> rllrr
|
|
309s [ 9880 evals] best 1.43611e-22 (fails 69) via crossover rlrr<->rlrr
|
|
345s [ 11000 evals] best 5.37852e-22 (fails 67) via place_missing n -> rllrrr
|
|
359s [ 11160 evals] best 5.45342e-22 (fails 67) via place_missing noop
|
|
359s [ 11400 evals] best 7.04364e-22 (fails 67) via crossover lrrlr<->lrrr
|
|
398s [ 12520 evals] best 2.63914e-21 (fails 65) via place_missing t -> rllrrrr
|
|
514s [ 16360 evals] best 1.955e-20 (fails 62) via undivide 1/lrrlr
|
|
533s [ 17000 evals] best 1.99161e-20 (fails 62) via crossover rrrr<->rrrr
|
|
542s [ 17320 evals] best 2.02902e-20 (fails 62) via core_undivide noop
|
|
543s [ 17400 evals] best 4.31819e-20 (fails 61) via rotate 0/lrrl
|
|
582s [ 18760 evals] best 1.53608e-19 (fails 59) via place_missing r -> llrll
|
|
599s [ 19160 evals] best 1.54019e-19 (fails 59) via core_undivide noop
|
|
646s [ 20840 evals] best 1.55586e-19 (fails 59) via level_compound_fix noop
|
|
700s [ 22840 evals] best 1.55593e-19 (fails 59) via level_compound_fix noop
|
|
719s [ 23320 evals] best 1.55798e-19 (fails 59) via level_fix noop
|
|
728s [ 23720 evals] best 1.5615e-19 (fails 59) via core_undivide noop
|
|
747s [ 24280 evals] best 1.57193e-19 (fails 59) via rotate 0/lrlr
|
|
769s [ 24920 evals] best 1.57705e-19 (fails 59) via level_compound_fix noop
|
|
780s [ 25400 evals] best 6.03009e-19 (fails 57) via place_missing t -> rllrrrr
|
|
807s [ 26200 evals] best 6.03785e-19 (fails 57) via level_fix noop
|
|
827s [ 27000 evals] best 6.0458e-19 (fails 57) via core_undivide noop
|
|
837s [ 27240 evals] best 6.0913e-19 (fails 57) via place_missing t -> rllrrrr
|
|
846s [ 27560 evals] best 6.11018e-19 (fails 57) via crossover rllrrrr<->rllrrrr
|
|
866s [ 28120 evals] best 6.13019e-19 (fails 57) via core_undivide noop
|
|
879s [ 28680 evals] best 6.50627e-19 (fails 57) via retype 1/llrlrl->st1
|
|
928s [ 30200 evals] best 6.52736e-19 (fails 57) via core_undivide noop
|
|
960s [ 31160 evals] best 6.55054e-19 (fails 57) via place_missing noop
|
|
980s [ 31720 evals] best 6.57339e-19 (fails 57) via crossover rllrr<->rllrr
|
|
1032s [ 33320 evals] best 6.59183e-19 (fails 57) via place_missing noop
|
|
1064s [ 34200 evals] best 6.60911e-19 (fails 57) via core_undivide noop
|
|
1080s [ 34600 evals] best 6.62724e-19 (fails 57) via place_missing noop
|
|
1101s [ 35160 evals] best 1.34695e-18 (fails 56) via level_retype 1/lrrrr<->0/rllrrl
|
|
1130s [ 36200 evals] best 1.35084e-18 (fails 56) via swap 1/llrr
|
|
1222s [ 39080 evals] best 1.3536e-18 (fails 56) via core_undivide noop
|
|
1263s [ 40280 evals] best 1.35887e-18 (fails 56) via retype 0/rrl->O
|
|
1296s [ 41240 evals] best 1.37684e-18 (fails 56) via place_missing noop
|
|
1317s [ 41960 evals] best 2.75612e-18 (fails 55) via core_undivide noop
|
|
1336s [ 42520 evals] best 2.76622e-18 (fails 55) via crossover llllrr<->llllrr
|
|
1354s [ 43160 evals] best 2.76719e-18 (fails 55) via core_undivide noop
|
|
1362s [ 43480 evals] best 2.7673e-18 (fails 55) via place_missing noop
|
|
1371s [ 44040 evals] best 2.76773e-18 (fails 55) via place_missing noop
|
|
1418s [ 45480 evals] best 2.89565e-18 (fails 55) via undivide 0/lrlr
|
|
1458s [ 46920 evals] best 2.89592e-18 (fails 55) via core_undivide noop
|
|
1478s [ 47480 evals] best 2.91016e-18 (fails 55) via divide 1/rlrlr
|
|
1688s [ 52600 evals] best 4.62272e-17 (fails 51) via place_missing n -> rllrl
|
|
1861s [ 56680 evals] best 4.63445e-17 (fails 51) via place_missing noop
|
|
1909s [ 58120 evals] best 4.736e-17 (fails 51) via crossover lrlrr<->lrll
|
|
1957s [ 58840 evals] best 4.75383e-17 (fails 51) via place_missing noop
|
|
1998s [ 60040 evals] best 4.77234e-17 (fails 51) via level_retype 0/rllrrrrr<->1/llrllrr
|
|
2024s [ 60680 evals] best 4.78944e-17 (fails 51) via place_missing noop
|
|
2094s [ 62200 evals] best 4.81054e-17 (fails 51) via core_undivide noop
|
|
2161s [ 63560 evals] best 7.68517e-16 (fails 47) via rotate 0/lrrl
|
|
2176s [ 63800 evals] best 7.7191e-16 (fails 47) via place_missing noop
|
|
2218s [ 64600 evals] best 7.75426e-16 (fails 47) via place_missing noop
|
|
2236s [ 64920 evals] best 7.79234e-16 (fails 47) via place_missing noop
|
|
2273s [ 65800 evals] best 7.82619e-16 (fails 47) via place_missing noop
|
|
2387s [ 67960 evals] best 7.86104e-16 (fails 47) via core_undivide noop
|
|
2485s [ 69560 evals] best 7.89754e-16 (fails 47) via swap 1/rlllr
|
|
2669s [ 72600 evals] best 7.9387e-16 (fails 47) via place_missing noop
|
|
2740s [ 74040 evals] best 1.09506e-15 (fails 46) via retype 0/rllll->st1
|
|
2755s [ 74440 evals] best 1.10394e-15 (fails 46) via crossover lr<->lr
|
|
2784s [ 74840 evals] best 1.11372e-15 (fails 46) via place_missing noop
|
|
2819s [ 75480 evals] best 1.12392e-15 (fails 46) via place_missing noop
|
|
2840s [ 75800 evals] best 1.13127e-15 (fails 46) via core_undivide noop
|
|
2948s [ 78040 evals] best 1.14356e-15 (fails 46) via place_missing noop
|
|
2965s [ 78600 evals] best 1.14876e-15 (fails 46) via place_missing noop
|
|
2977s [ 78760 evals] best 1.15416e-15 (fails 46) via core_undivide noop
|
|
3017s [ 79720 evals] best 1.15977e-15 (fails 46) via place_missing noop
|
|
3081s [ 81400 evals] best 1.16386e-15 (fails 46) via rotate 0/rr
|
|
3096s [ 81640 evals] best 1.16556e-15 (fails 46) via level_retype 0/rlllr<->1/llrlrr
|
|
3121s [ 82360 evals] best 1.17153e-15 (fails 46) via swap 0/rlrlr
|
|
3184s [ 84040 evals] best 1.17767e-15 (fails 46) via core_undivide noop
|
|
3222s [ 85000 evals] best 1.18184e-15 (fails 46) via core_undivide noop
|
|
3245s [ 85480 evals] best 1.18814e-15 (fails 46) via place_missing noop
|
|
3301s [ 86840 evals] best 1.19454e-15 (fails 46) via crossover lrrr<->lrrr
|
|
3313s [ 87080 evals] best 1.201e-15 (fails 46) via place_missing noop
|
|
3365s [ 88360 evals] best 1.20745e-15 (fails 46) via place_missing noop
|
|
3467s [ 90520 evals] best 1.2138e-15 (fails 46) via crossover rlrlrl<->rlrlrr
|
|
3481s [ 91000 evals] best 1.21994e-15 (fails 46) via core_undivide noop
|
|
3508s [ 91560 evals] best 1.22574e-15 (fails 46) via core_undivide noop
|
|
3508s [ 91640 evals] best 8.63614e-15 (fails 43) via level_retype 1/llll<->0/rrl
|
|
3730s [ 97080 evals] best 8.69346e-15 (fails 43) via swap 0/llllr
|
|
3756s [ 97720 evals] best 8.7509e-15 (fails 43) via place_missing noop
|
|
3858s [100360 evals] best 8.80776e-15 (fails 43) via rotate 0/llllr
|
|
3882s [100760 evals] best 8.86311e-15 (fails 43) via core_undivide noop
|
|
3896s [101080 evals] best 1.70808e-14 (fails 42) via crossover lrrrr<->lrll
|
|
3921s [101880 evals] best 1.71667e-14 (fails 42) via place_missing noop
|
|
4057s [105240 evals] best 1.72459e-14 (fails 42) via crossover lrlr<->lrlr
|
|
4132s [107320 evals] best 1.73156e-14 (fails 42) via place_missing noop
|
|
4145s [107720 evals] best 1.73708e-14 (fails 42) via place_missing noop
|
|
4196s [109000 evals] best 1.74162e-14 (fails 42) via place_missing noop
|
|
4233s [109800 evals] best 1.74389e-14 (fails 42) via place_missing noop
|
|
4272s [110760 evals] best 1.74447e-14 (fails 42) via place_missing noop
|
|
4336s [112520 evals] best 1.75219e-14 (fails 42) via rotate 0/rlrlr
|
|
4361s [112920 evals] best 1.75253e-14 (fails 42) via undivide 1/llrllr
|
|
4415s [114440 evals] best 1.76097e-14 (fails 42) via core_undivide noop
|
|
4451s [115320 evals] best 1.76189e-14 (fails 42) via crossover rlr<->rlr
|
|
4489s [116200 evals] best 1.77166e-14 (fails 42) via place_missing noop
|
|
4514s [116840 evals] best 1.78312e-14 (fails 42) via place_missing noop
|
|
4576s [118360 evals] best 1.78941e-14 (fails 42) via place_missing noop
|
|
4740s [122600 evals] best 1.79859e-14 (fails 42) via rotate 1/llrlr
|
|
4792s [123880 evals] best 3.50161e-14 (fails 41) via divide 1/llrlrl
|
|
4815s [124440 evals] best 3.51369e-14 (fails 41) via place_missing noop
|
|
4827s [124840 evals] best 3.5156e-14 (fails 41) via core_undivide noop
|
|
5698s [146680 evals] best 3.52342e-14 (fails 41) via swap 1/llrlrl
|