faeval.git/experiments/prefit_threshold_curve.py, branch master Unnamed repository; edit this file 'description' to name the repository. Add Phase 10A: no prefit threshold — even random Vec blend beats DFA by +1.3% 2026-03-26T13:37:39+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-03-26T13:37:39+00:00 ef4aed70130e2212b4ed1cb7212e2ea6c7c7adb2 E_prefit=0 (random Vec) + blend(0.75): 32.4% vs DFA 31.1% (+1.3%) E_prefit=15: 32.3% (+1.2%) E_prefit=60: 32.5% (+1.4%) Frozen Gamma/rho near zero at all prefit levels. The Phase 9A success was NOT from Vec learning useful credit — it was from the blend mechanism itself providing regularization/diversification over pure DFA. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
E_prefit=0 (random Vec) + blend(0.75): 32.4% vs DFA 31.1% (+1.3%)
E_prefit=15: 32.3% (+1.2%)
E_prefit=60: 32.5% (+1.4%)

Frozen Gamma/rho near zero at all prefit levels. The Phase 9A success was NOT
from Vec learning useful credit — it was from the blend mechanism itself providing
regularization/diversification over pure DFA.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>