diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 13:37:49 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 13:37:49 -0500 |
| commit | 3f3045c7920d9c2d55ce3b4d428a06ebc89350fe (patch) | |
| tree | f7d5b5fe965cf32ce142324192cd593e193fc3f1 /MIRROR_BASELINE.md | |
| parent | 37cf78b7f696c9eedc0745ebdaa656bff0ab2f81 (diff) | |
results: pass normalized mirror causal-capture gate
Diffstat (limited to 'MIRROR_BASELINE.md')
| -rw-r--r-- | MIRROR_BASELINE.md | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/MIRROR_BASELINE.md b/MIRROR_BASELINE.md index c7ad348..0532955 100644 --- a/MIRROR_BASELINE.md +++ b/MIRROR_BASELINE.md @@ -84,3 +84,19 @@ cost at most 1.15x BP is considered a strong inherited baseline. It does not authorize test access; it instead opens design of a hierarchical innovation intervention on the same frozen recipe. +## Audited WM-1 outcome (2026-07-22) + +All four records are finite and every frozen capture check passes. The selected +rate is `eta_M=0.1`: + +| rule | early alignment | all-layer alignment | feedback/forward cosine | norm range | +|:--|--:|--:|--:|:--| +| fixed HFA | -0.000263 | 0.011279 | 0.001614 | [0.959, 1.055] | +| WM 0.03 | 0.075263 | 0.235197 | 0.625186 | [0.697, 0.787] | +| WM 0.10 | **0.446141** | **0.542159** | **0.915480** | **[0.889, 1.157]** | +| WM 0.30 | 0.112177 | 0.228114 | 0.853343 | [0.999, 1.697] | + +Each learned record uses 20 local observations, zero logical task-loss queries, +and estimated work `1.6305e9` MACs. WM-1 status is `passed`; WM-2 opens with +the predeclared `eta_M=0.1`. No validation accuracy was used for this selection +and CIFAR-10 test remains untouched. |