diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 08:52:08 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 08:52:08 -0500 |
| commit | 0dc89449af7307516372fe2b0463c11484a695e1 (patch) | |
| tree | 73ef9f2bc29151ca5408b6564ce65f2d527bb9ce /experiments/minimal_scaffold_replication.py | |
| parent | 6016484e9f16e220660ed6e028f4417a26cd3fee (diff) | |
Appendix G + J: 3-seed depth scan L=4 validation + SB/CB random_targets 100ep convergence
- Appendix G: depth scan L=4 now 3-seed (s42, s123, s456). 3-seed DFA layer-0 cos
+0.412±0.011, deep cos -0.0004±0.0008, CB deep cos +0.039±0.010. Indistinguishable
from single-seed row shown in table.
- Appendix J: full 100-epoch random_targets trajectory for SB and CB:
SB: ||h_L||=3.6e5, ||g_L||=4e-8 (at floor), acc 0.100 (chance)
CB: ||h_L||=1.38e8, ||g_L||=0 (collapsed), acc 0.085 (chance)
Both reach Mode 1 (a)+(b) at 100ep, consistent with DFA's 1.67e8 / 8e-12.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'experiments/minimal_scaffold_replication.py')
0 files changed, 0 insertions, 0 deletions