faeval.git/experiments/snapshot_time_sweep.py, branch master Unnamed repository; edit this file 'description' to name the repository. Add Phase 7A: snapshot time sweep shows early snapshots have positive held-out transfer 2026-03-25T15:23:19+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-03-25T15:23:19+00:00 ef5bd494087a46ee80d8bc17796074efdae81ff4 At epoch 5 (acc=49%), Vec_M4 5-step: dL_held=-0.005 (PUR=0.70) Oracle BP 5-step: dL_held=-0.009 (PUR=1.05) DFA 5-step: dL_held=+0.003 (always hurts held-out) By epoch 20, generalization window closes. Held-out failure is late-snapshot artifact. Better credit → lower update variance (Vec=0.8 vs DFA=40), not higher. Key implication: DFA warmup delays credit bridge past its useful window. Credit should be used from epoch 0, not after 20% warmup. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
At epoch 5 (acc=49%), Vec_M4 5-step: dL_held=-0.005 (PUR=0.70)
  Oracle BP 5-step: dL_held=-0.009 (PUR=1.05)
  DFA 5-step: dL_held=+0.003 (always hurts held-out)

By epoch 20, generalization window closes. Held-out failure is late-snapshot artifact.
Better credit → lower update variance (Vec=0.8 vs DFA=40), not higher.

Key implication: DFA warmup delays credit bridge past its useful window.
Credit should be used from epoch 0, not after 20% warmup.

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