From 590baa92c66caeb939bae3fad0ed7cc9b2c87f75 Mon Sep 17 00:00:00 2001
From: YurenHao0426 <Blackhao0426@gmail.com>
Date: Thu, 28 May 2026 22:51:23 -0500
Subject: Add capacity scaling calculations

---
 notes/02_experiment_notes.md | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'notes')

diff --git a/notes/02_experiment_notes.md b/notes/02_experiment_notes.md
index b7f17a5..ab69cd8 100644
--- a/notes/02_experiment_notes.md
+++ b/notes/02_experiment_notes.md
@@ -235,3 +235,27 @@ Result:
 - KS p-value: `0.633285`
 
 This is a clean first-pass validation for the isotropic Gaussian case.
+
+## Scaling Run Log
+
+Script:
+
+```bash
+python scripts/capacity_scaling.py --plot
+```
+
+Default sweep:
+
+- widths: `16, 32, 64, 128`
+- feedback-aligned layer counts: `1, 2, 4, 8, 16`
+- fixed threshold: \(q=0.01\)
+- chance-level threshold: \(q=1/D\)
+- log unit: nats
+
+Result:
+
+- rows written: `40`
+- fixed-threshold max total cost: `1361.74` nats at width `128`, layers `16`
+- chance-level max total cost: `18.3652` nats at width `128`, layers `16`
+
+This cleanly separates the fixed-threshold regime, where total cost scales like \(Ln^2\), from the chance-level regime, where per-layer cost is nearly width-independent.
-- 
cgit v1.2.3