summaryrefslogtreecommitdiff
path: root/results
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-04-07 23:29:13 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-04-07 23:29:13 -0500
commit9f7424553392e2f4b9f6e90a71b3b6e1e52f303f (patch)
treef3bba04c1490d1a722a6a42507a68b4c5a5217d6 /results
parent665c9bb4ab3a5126c6fc191eecf42be7b703eb0c (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.pngbin0 -> 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
new file mode 100644
index 0000000..a821ccd
--- /dev/null
+++ b/results/protocol_audit/figure_audit_5method.png
Binary files differ