From 26407ca3e958ef3701cc69afae4973f023b5b19e Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 03:02:55 -0500 Subject: experiments: freeze FashionMNIST C1 recovery --- ROADMAP.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 5864064..ee89703 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -61,6 +61,21 @@ innovation gain of at least 2 points over norm-matched raw, mean traffic R2 of a mean final hidden-layer teaching alignment of at least 0.1. The mean paired no-traffic innovation change relative to both raw controls must be no worse than -0.5 points. +After the MNIST near-miss, one independent FashionMNIST recovery is frozen before any new result. +The validation screen uses model seed 0, a 5,000-example stratified split from training data +(`split_seed=2027`), d3/w256, 15 epochs, and otherwise the exact MNIST protocol. It crosses soma +traffic at `rho=0.5` and top-down traffic at `rho in {0.2, 0.5}`, each with projection seeds 1234 +and 5678 and all four signal controls; a no-traffic panel has three controls (27 runs total). +Only final validation accuracy is observed; diagnostics use the fixed training prefix. + +Soma traffic is eligible only if both projections gain at least 2 points over norm-matched raw, +retain accuracy within 3 points of no traffic, have traffic R2 at least 0.5, and alignment at least +0.1. A top-down level is eligible only if both its projections meet the same criteria. Among +eligible levels, select the one with the highest worst-projection gain, breaking an exact tie +toward smaller `rho`. No-traffic harm must remain within 0.5 points. If soma or no top-down level +is eligible, stop without evaluating FashionMNIST test. Otherwise freeze that level for a +five-model-seed, 95-run test confirmation under the original C1 per-realization gate. + ### C2. SDIL scales when depth is useful Flattened CIFAR is retained as a preservation result, not as evidence that added depth is used. -- cgit v1.2.3