faeval.git/report_explore/MEMO_10A6_structured_vs_semantic.md, branch master Unnamed repository; edit this file 'description' to name the repository. Add Phase 10A.6: gain requires trainable depth-aware aux, not semantic credit 2026-03-27T03:07:35+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-03-27T03:07:35+00:00 b4e3cbeae6cb4cf4a4b69b84a475afcd7d7e9dbe 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> 
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>