diff options
Diffstat (limited to 'RESULTS.md')
| -rw-r--r-- | RESULTS.md | 18 |
1 files changed, 18 insertions, 0 deletions
@@ -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 |