faeval.git/results/protocol_audit/figure_audit_5method.png, branch master Unnamed repository; edit this file 'description' to name the repository. Add §2/§3 hero figure: 5-method audit horizontal bar chart 2026-04-08T04:29:13+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-08T04:29:13+00:00 9f7424553392e2f4b9f6e90a71b3b6e1e52f303f 4-panel layout (one per diagnostic), 5 methods sorted bottom-to-top by ascending accuracy, color-coded healthy (BP/EP, blue) vs degenerate (DFA/SB/CB, red), with threshold lines drawn: (a) max per-block growth (log scale, threshold 50x) (b) ||g_L|| (log scale, floor 1e-7) (c) cross-batch stability (linear, ceiling 0.30) (d) headline acc (linear, frozen baseline 0.349) The visual layout makes it immediately obvious that: - (a) and (b) cleanly split healthy from degenerate (4-7 OOM gap) - (c) is bimodal and doesn't cleanly split — confirms it's a sub-mode discriminator, not a primary detector - (d) shows BP above the frozen baseline by ~25 pp while DFA/CB/SB are at or below it 
4-panel layout (one per diagnostic), 5 methods sorted bottom-to-top by
ascending accuracy, color-coded healthy (BP/EP, blue) vs degenerate
(DFA/SB/CB, red), with threshold lines drawn:

  (a) max per-block growth (log scale, threshold 50x)
  (b) ||g_L|| (log scale, floor 1e-7)
  (c) cross-batch stability (linear, ceiling 0.30)
  (d) headline acc (linear, frozen baseline 0.349)

The visual layout makes it immediately obvious that:
  - (a) and (b) cleanly split healthy from degenerate (4-7 OOM gap)
  - (c) is bimodal and doesn't cleanly split — confirms it's a sub-mode
    discriminator, not a primary detector
  - (d) shows BP above the frozen baseline by ~25 pp while DFA/CB/SB
    are at or below it