diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-26 22:07:35 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-26 22:07:35 -0500 |
| commit | b4e3cbeae6cb4cf4a4b69b84a475afcd7d7e9dbe (patch) | |
| tree | fca5a27504471091eba74a8f7efe2cf48eb85826 /experiments/checkpointed_handoff.py | |
| parent | 610e1169e19378cccd2d9b92a588c24dca7f3df7 (diff) | |
Add Phase 10A.6: gain requires trainable depth-aware aux, not semantic credit
9-branch dissection results:
- zero_target crashes (-9.1%): aux must output non-zero
- constant_input neutral (+0.0%): needs at least depth info
- time_only works (+1.0%): h_l not needed, just depth index
- shuffled/fresh_random work (+1.3-1.4%): no semantic content needed
- prefit60_trainable ≈ random_trainable: prefit adds nothing
- All frozen branches crash: trainability is essential
Mechanism: depth-aware trainable auxiliary perturbation that diversifies
block-local updates. Not semantic credit, not pure trainability.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'experiments/checkpointed_handoff.py')
0 files changed, 0 insertions, 0 deletions