From 82d49f4b8b741669ab39100f4719719801064f20 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 15:08:36 -0500 Subject: results: record residual mirror full failure --- RESULTS.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index 76ffc29..e2426af 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -868,6 +868,24 @@ so the single RRM-3 full validation run opens. The 9.86-point gap despite nearly perfect instantaneous alignment is retained as a negative diagnostic rather than treating cosine as a proxy for optimization equivalence. +The conditional RRM-3 full run then fails. It ends at 10.00% validation +accuracy with NaN validation loss, despite endpoint early/all-layer alignment +`0.877435/0.848738`, feedback/forward cosine `0.999998`, and a tightly +controlled `[1.000157,1.002447]` feedback/forward norm range. Training loss +rises from `2.6107` to `1.5808e16` at epoch 92; the two learning-rate drops +reduce the reported epoch mean to `8.9503e13` without recovering learning. +It uses zero task-loss queries and `0.9969x` BP MACs, so neither cost nor final +alignment explains away the failure. The frozen RRM branch is closed and no +test endpoint is touched. + +This is direct evidence that endpoint alignment can be a false certificate for +an intermittent tracker. If task weights move by `U_m` between mirror events, +the ideal tracking error follows `E_(m+1)=(1-eta_M)E_m-U_m`; once task motion +slows, the final error can vanish even after the high-rate trajectory has +already destabilized the model. This baseline negative does not lower or raise +the SDIL score because the separate KP substrate remains under its own frozen +gate. + ### Modified Kolen--Pollack reciprocal baseline The independently implemented Akrout et al. reciprocal-plasticity baseline -- cgit v1.2.3