diff options
Diffstat (limited to 'NOTE.md')
| -rw-r--r-- | NOTE.md | 20 |
1 files changed, 19 insertions, 1 deletions
@@ -5,7 +5,7 @@ - **pilot**: Controlled iteration (commits 0b9ebb2, 7baf7ae) - **frozen**: Code at commit 0b9ebb2 for all reported results -## Status: PHASE 9A — BLEND HANDOFF OUTPERFORMS DFA (+0.55%) +## Status: PHASE 9A FULL — BLEND(0.75) OUTPERFORMS DFA BY +1.5% --- @@ -504,5 +504,23 @@ This is Case B: pure Vec handoff fails, but blend works. Vec provides complementary directional credit that DFA alone lacks. DFA stabilizes the trajectory while Vec adds learned corrections. +### Full Phase 9A Results (seed=42, all t0 × alpha) + +| t0 | Branch | final acc | diff vs DFA | +|----|--------|-----------|-------------| +| 1 | continue_DFA | 0.310 | — | +| 1 | blend_05 | **0.319** | **+0.9%** | +| 1 | blend_075 | 0.313 | +0.3% | +| 5 | continue_DFA | 0.310 | — | +| 5 | blend_05 | 0.317 | +0.6% | +| 5 | **blend_075** | **0.326** | **+1.5%** | +| 10 | continue_DFA | 0.310 | — | +| 10 | blend_05 | 0.318 | +0.7% | +| 10 | **blend_075** | **0.325** | **+1.4%** | + +**Best config: t0=5 or 10, blend alpha=0.75 (75% Vec + 25% DFA), +1.5%.** +Higher Vec fraction (0.75) outperforms lower (0.25, 0.5) at t0=5,10. +Pure Vec handoff still fails at all t0. + ### Experiment IDs (Phase 9) - `checkpointed_handoff/`: Phase 9A checkpointed handoff with branches |