faeval.git/results/dfa_pen_short/dfa_pen_lam0.01_s456.json, branch master Unnamed repository; edit this file 'description' to name the repository. 3-seed multi-seed verification of penalized DFA deep cos = +0.17 2026-04-08T06:31:16+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-08T06:31:16+00:00 02252d942dbf449276059c49260ec0994c4f9a5d | seed | l0 | l1 | l2 | l3 | l4 | layer-mean | |---|---:|---:|---:|---:|---:|---:| | 42 | +0.316 | +0.169 | +0.151 | +0.165 | +0.166 | +0.193 | | 123 | +0.333 | +0.093 | +0.155 | +0.178 | +0.177 | +0.187 | | 456 | +0.339 | +0.131 | +0.123 | +0.150 | +0.150 | +0.179 | 3-seed mean deep cos (l1-l4): ~0.155 ± 0.025 3-seed layer-mean: +0.186 ± 0.007 The +0.17 finding is rock-solid, combined with: - null calibration: training-Bs +0.16 vs fresh-Bs +0.002 - hypothesis B confirmed: vanilla early ep deep cos ~0 - 3-seed reproducibility (this commit) This is the §4 evidence for the paper's 'penalty creates partial deep alignment, partially alleviating mode 2'. 
| seed | l0 | l1 | l2 | l3 | l4 | layer-mean |
|---|---:|---:|---:|---:|---:|---:|
| 42 | +0.316 | +0.169 | +0.151 | +0.165 | +0.166 | +0.193 |
| 123 | +0.333 | +0.093 | +0.155 | +0.178 | +0.177 | +0.187 |
| 456 | +0.339 | +0.131 | +0.123 | +0.150 | +0.150 | +0.179 |

3-seed mean deep cos (l1-l4): ~0.155 ± 0.025
3-seed layer-mean: +0.186 ± 0.007

The +0.17 finding is rock-solid, combined with:
  - null calibration: training-Bs +0.16 vs fresh-Bs +0.002
  - hypothesis B confirmed: vanilla early ep deep cos ~0
  - 3-seed reproducibility (this commit)

This is the §4 evidence for the paper's 'penalty creates partial deep
alignment, partially alleviating mode 2'.