diff options
Diffstat (limited to 'HFA_BASELINE.md')
| -rw-r--r-- | HFA_BASELINE.md | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/HFA_BASELINE.md b/HFA_BASELINE.md index 1dc5f87..64d9c22 100644 --- a/HFA_BASELINE.md +++ b/HFA_BASELINE.md @@ -62,3 +62,16 @@ test-set evaluation. - HFA-S2, if opened, copies the selected S1 hidden rate mechanically and does not select on intermediate validation accuracy. +## Audited outcome (2026-07-22) + +All three HFA-S1 trajectories are finite and test-free. Validation accuracy +increases monotonically over the frozen hidden-rate grid: `39.64%` at 0.01, +`41.58%` at 0.03, and `43.52%` at 0.1. The selected 0.1 run has early-third +teaching alignment `0.040406`, zero causal queries, 267,904 fixed feedback +parameters, and estimated work `2.4242e13` MACs. + +The selected endpoint exceeds matched DFA by `6.36` points and the failed-v1 +short SDIL endpoint by `1.54` points, but misses the preregistered 50% HFA-S2 +threshold by `6.48` points. Status is `selected_full_closed`; the 200-epoch HFA +run is not launched, no extra HFA setting is allowed, and CIFAR-10 test remains +untouched. |