summaryrefslogtreecommitdiff
path: root/results/confirmatory/C2_energy_concentration.csv
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-04-26 11:03:29 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-04-26 11:03:29 -0500
commit1c172f7d038eedd3d828d453e852c060072f52c8 (patch)
tree3d7cf500dca3c0cb35f577b87c236559b58c3eef /results/confirmatory/C2_energy_concentration.csv
parent6f88add7aed62152ed6776765917e03d5096a5cc (diff)
CIFAR-100 per-seed diagnostics complete — full qualifying table
CIFAR-100, d=256 L=4, 100ep, 3 seeds. Frozen baseline (BP-frozen) = 0.178. acc (±ddof=1) cos (±ddof=1) h_L g_L <frozen? BP 0.321 ± 0.002 +1.000 ~192 ~9.5e-4 no FA 0.133 ± 0.013 +0.234 ± 0.015 ~1e5-7e5 ~1e-6 YES (all 3) DFA 0.088 ± 0.001 +0.029 ± 0.001 ~2e8 ~9e-9 YES (all 3) Frozen 0.178 — — — baseline Both FA and DFA are below frozen at ALL 3 seeds with positive cosine. FA cos is +0.23 (clearly positive). DFA cos is +0.03 (small but positive). Both are well above chance (1% for 100 classes). BP is ~0.32, well above frozen (trustworthy control). This is the paper's strongest qualifying setting because it uses the SAME architecture (d=256 L=4) as the main CIFAR-10 audit — only the task difficulty changes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'results/confirmatory/C2_energy_concentration.csv')
0 files changed, 0 insertions, 0 deletions