Update README.md

README.md

@@ -233,6 +233,36 @@ if __name__ == "__main__":
             print(f"{row['D']:5d}  {row['avg_cv']:8.4f}  {row['in_band_pct']:5.1f}%  {row['status']}")
 ```
 
+## Large Vocabulary Ablation
+
+The CV is consistent with the findings and deterministically sample-capable for validity and conjunctive utility.
+
+```
+D=32 fixed. CV across vocab sizes.
+Pool capped at 512 for fair comparison.
+============================================================
+  V=        32  D=32  CV=0.2578  0.1s  0MB
+  V=       512  D=32  CV=0.2615  0.0s  0MB
+  V=     8,192  D=32  CV=0.2578  0.0s  1MB
+  V=    65,536  D=32  CV=0.2663  0.0s  8MB
+  V=   131,072  D=32  CV=0.2590  0.0s  17MB
+  V=   500,000  D=32  CV=0.2745  0.1s  64MB
+  V= 1,000,000  D=32  CV=0.2645  0.2s  128MB
+  V= 4,000,000  D=32  CV=0.2541  0.9s  512MB
+  V=13,000,000  D=32  CV=0.2681  2.9s  1664MB
+
+============================================================
+Now uncapped pool (sample from ALL embeddings):
+============================================================
+  V=       512  D=32  CV=0.2591  pool=512
+  V=     8,192  D=32  CV=0.2427  pool=8192
+  V=    65,536  D=32  CV=0.2684  pool=65536
+  V=   500,000  D=32  CV=0.2562  pool=500000
+```
+
+
+
+
 ## Implications for Architecture Design
 
 The band is not a training outcome. It is a geometric property of dimensionality. This means: