vvs/sim-numerics
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

PREREG_close_sub outcome - the ONE check on the fourth corpus (server): A' TRANSFERS. 240 problems: A' 3656 vs Chandrupatla 5717 (-36%), per problem 177/35/28 p=1e-27, guarantee held (Brent 50 and TOMS748 37 violations), all solved; A' below A (4547). Without the targeted classes: 2403 vs 3569, 107/31/22 p=1e-14. Ablation: sub earned (+893, D3 1807 -> 924), close NOT earned on this corpus (-2) though it earned on the seen applied corpus. Per class vs Chandrupatla: D1 random polynomial simple root 20/8/12 (433 vs 419), D2 multiple 39/1/0, D3 fractional power 37/1/2, D4 exp+sin sums 23/14/3, D5 compositions 25/8/7 (503 vs 1017), D6 odd around the root 33/3/4.

Browse Source 
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
vvs
2026-09-21 20:08:29 +01:00
co-authored by Claude Opus 5
parent 8027d7f5ef
commit 6d2531e6ea
2 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
results_fourth.txt
+23
View File
@@ -0,0 +1,23 @@
FOURTH corpus (the one check)
base total 7711 solved 240/240 violations 0
A total 4547 solved 240/240 violations 0
Aprime total 3656 solved 240/240 violations 0
Aprime-close total 3654 solved 240/240 violations 0
Aprime-sub total 4549 solved 240/240 violations 0
chandrupatla total 5717 solved 240/240 violations 0
brent total 8267 solved 240/240 violations 50
toms748 total 8084 solved 240/240 violations 37
F1 ✓ (3656 vs 5717, -36.1%) F2 ✓ (177/35/28 p=1.2e-27) F3 ✓ F4 ✓ (A' 3656 vs A 4547) -> A' TRANSFERS
ablation - close: -2 (NOT earned)
ablation - sub: +893 (earned)
without the targeted classes (D1 D2 D4 D5): A' 2403 vs Ch 3569 107/31/22 p=1.3e-14
vs brent 3656 vs 8267 143/60/37 p=6.6e-16
vs toms748 3656 vs 8084 178/44/18 p=2.8e-34
per class: A' / A / Chandrupatla / Brent / TOMS748 (A' vs Ch w/t/l)
D1: 433 / 433 / 419 / 474 / 476 20/8/12
D2: 1163 / 1154 / 1805 / 4398 / 3860 39/1/0
D3: 924 / 1807 / 1784 / 1172 / 1553 37/1/2
D4: 304 / 307 / 328 / 324 / 343 23/14/3
D5: 503 / 507 / 1017 / 1556 / 1477 25/8/7
D6: 329 / 339 / 364 / 343 / 375 33/3/4
fourth done
sweep_fourth_fourth.json
+1
View File
File diff suppressed because one or more lines are too long