diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-07 23:29:13 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-07 23:29:13 -0500 |
| commit | 9f7424553392e2f4b9f6e90a71b3b6e1e52f303f (patch) | |
| tree | f3bba04c1490d1a722a6a42507a68b4c5a5217d6 /results | |
| parent | 665c9bb4ab3a5126c6fc191eecf42be7b703eb0c (diff) | |
Add §2/§3 hero figure: 5-method audit horizontal bar chart
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
Diffstat (limited to 'results')
| -rw-r--r-- | results/protocol_audit/figure_audit_5method.png | bin | 0 -> 81228 bytes |
1 files changed, 0 insertions, 0 deletions
diff --git a/results/protocol_audit/figure_audit_5method.png b/results/protocol_audit/figure_audit_5method.png Binary files differnew file mode 100644 index 0000000..a821ccd --- /dev/null +++ b/results/protocol_audit/figure_audit_5method.png |
