From 0660bd1f6274e7982438506eec67870b105a0285 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 04:58:05 -0500 Subject: results: close calibration quality recovery --- RESULTS.md | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index 2affc24..b0ac5dd 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -384,6 +384,27 @@ This is a diagnosis and upper-cost baseline, not the proposed scalable method. A `68.4x` ordinary training work, with `108.2` seconds mean wall time. The next recovery must retain the vectorizer and disclose how much of this query burden it avoids. +### Calibration-quality development screen (task seed 0 only) + +The first post-diagnosis development screen kept the context vectorizer and concurrent A/W updates +fixed, replacing simultaneous K1/e4 calibration by layerwise K4/e4 or K16/e4. The frozen rule +selected the higher mean d4 endpoint, preferring K4 within one point; all three model seeds and +both depths are retained. + +| directions | depth | validation acc (%) | depth gain | d4 lesion drop | d4 work / ordinary | +|-----------:|------:|-------------------:|-----------:|----------------:|-------------------:| +| K4 | 1 | 66.217 ± 5.264 | — | — | — | +| K4 | 4 | 65.633 ± 27.078 | -0.583 | +13.733 | 5.5x | +| K16 | 1 | 65.917 ± 4.753 | — | — | — | +| K16 | 4 | 65.567 ± 26.962 | -0.350 | +14.033 | 18.2x | + +Only one of three depth pairs and one of three d4 lesions are positive for either candidate. K16 +has one nonfinite d4 final loss and is ineligible; K4 is selected mechanically but is not advanced +to independent confirmation because its mean depth gain is negative. **Better per-event causal +targets do not by themselves cure the coupled A/W basin.** The next bounded development question +is temporal: calibrate A while W is held fixed, then open forward plasticity and maintain A with +the already selected low-query simultaneous schedule. + ## Paper-faithful non-backprop baselines `PETITE` in the initial request is treated as **PEPITA**. Implementations and hyperparameters were -- cgit v1.2.3