faeval.git/results/dfa_pen_short/dfa_pen_lam0.1_s42.json, branch master Unnamed repository; edit this file 'description' to name the repository. λ sweep on penalty strength: lam ∈ {1e-4, 1e-2, 1e-1} cos + rho results 2026-04-08T08:22:36+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-08T08:22:36+00:00 25ee60c8277ba82b9cb6471471b1a727e0712ea7 Round 19's #5 recommendation. Major new finding for the paper: | lam | acc | ||h_L|| | ||g_2|| | deep cos | deep rho | |-------|------:|--------:|--------:|---------:|---------:| | 0 | 0.308 | 4e8 | 5e-10 | -0.008 | -0.003 | | 1e-4 | 0.359 | 2.4e4 | 6.3e-7 | -0.022 | -0.004 | | 1e-2 | 0.363 | 4e4 | 1e-6 | +0.155 | +0.080 | | 1e-1 | 0.349 | 1.2e4 | 1.6e-6 | +0.131 | +0.067 | KEY: at lam=1e-4 the residual stream is contained AND ||g|| is healthy (mode 1 ALLEVIATED), but deep cos and rho are still essentially zero (mode 2 NOT alleviated). This is independent dissociation of the two modes via penalty strength: at weak penalty you get mode 1 fix WITHOUT mode 2 fix. Both metrics (cos, rho) agree at every lambda. Penalty strength has a non-monotonic effect on mode 2 alleviation: - lam=1e-4: too weak, mode 2 not alleviated (cos ~0) - lam=1e-2: sweet spot, cos +0.16, rho +0.08 - lam=1e-1: slightly over-constrained, cos +0.13, rho +0.07 This is the 7th independent validation of the two-mode separation, and the strongest one because it shows mode 1 alleviation WITHOUT mode 2 alleviation — the modes do not even respond to the same intervention strength. 
Round 19's #5 recommendation. Major new finding for the paper:

| lam   | acc   | ||h_L|| | ||g_2|| | deep cos | deep rho |
|-------|------:|--------:|--------:|---------:|---------:|
| 0     | 0.308 | 4e8     | 5e-10   | -0.008   | -0.003   |
| 1e-4  | 0.359 | 2.4e4   | 6.3e-7  | -0.022   | -0.004   |
| 1e-2  | 0.363 | 4e4     | 1e-6    | +0.155   | +0.080   |
| 1e-1  | 0.349 | 1.2e4   | 1.6e-6  | +0.131   | +0.067   |

KEY: at lam=1e-4 the residual stream is contained AND ||g|| is healthy
(mode 1 ALLEVIATED), but deep cos and rho are still essentially zero
(mode 2 NOT alleviated). This is independent dissociation of the two
modes via penalty strength: at weak penalty you get mode 1 fix WITHOUT
mode 2 fix.

Both metrics (cos, rho) agree at every lambda. Penalty strength has a
non-monotonic effect on mode 2 alleviation:
  - lam=1e-4: too weak, mode 2 not alleviated (cos ~0)
  - lam=1e-2: sweet spot, cos +0.16, rho +0.08
  - lam=1e-1: slightly over-constrained, cos +0.13, rho +0.07

This is the 7th independent validation of the two-mode separation, and
the strongest one because it shows mode 1 alleviation WITHOUT mode 2
alleviation — the modes do not even respond to the same intervention
strength.