Upload README.md with huggingface_hub

README.md

@@ -149,16 +149,32 @@ print(f"sim(Anchor, Paraphrase) = {sim_paraphrase:.4f}")
 print(f"sim(Anchor, Unrelated)  = {sim_unrelated:.4f}")
 ```
 
----
-
 ## 📐 Architecture & Principles
 
-1. **Multiscale Manifold Representation:** Text is lifted into a high-dimensional subword coordinate space that captures character-level roots, word identity, and compositional syntax without tokenization overhead.
-2. **Spectral Subspace Compression:** A pre-distilled linear projection maps sparse text representations into the principal semantic directions of the teacher model:
-   $$z = W x + b, \qquad W \in \mathbb{R}^{60 \times 16384}$$
-3. **Hyperspherical Normalization:** Embeddings are constrained to the unit sphere $\mathbb{S}^{59}$:
-   $$\hat{z} = \frac{z}{\lVert z \rVert_{2}}$$
-4. **Calibrated Metric Space:** Semantic distances are decoded through an anisotropic metric tensor $M$ optimized for fine-grained semantic discrimination.
+### 1. Multiscale Manifold Representation
+Text is deterministically lifted into a high-dimensional subword coordinate space that captures character-level roots, word identity, and compositional syntax without tokenization overhead.
+
+### 2. Spectral Subspace Compression
+A pre-distilled linear projection maps sparse text representations into the principal semantic directions of the teacher model:
+
+$$
+z = W x + b, \qquad W \in \mathbb{R}^{60 \times 16384}
+$$
+
+### 3. Hyperspherical Normalization
+Embeddings are constrained to the 59-dimensional unit hypersphere $\mathbb{S}^{59}$:
+
+$$
+\hat{z} = \frac{z}{\|z\|_2}
+$$
+
+### 4. Calibrated Metric Space
+Semantic distances are decoded through an anisotropic metric tensor $M$ optimized for fine-grained semantic discrimination:
+
+$$
+\mathcal{D}(a, b) = \exp\left(-\sqrt{\sum_{k=1}^{60} M_{kk} (a_k - b_k)^2}\right)
+$$
+
 
 ---