Fix model card formatting (replace raw LaTeX with clean Unicode and code spans)

README.md

@@ -25,12 +25,12 @@ It specializes the 12-layer Givens Rotational Transformer backbone for:
 
 ## Code & Tool-Calling Alignment Metrics
 
-- **Held-Out Code & Tool-Call Validation Perplexity**: `54.93` (`val_loss = 4.0061` base) $\rightarrow$ **`1.7632`** (`val_loss = 0.5672` w/ `HuygensAdam`; `1.8253` w/ `PairAdam`, `1.8619` w/ `GyricAdam`)
-- **Held-Out Python Code Token Top-1 Accuracy**: `46.80%` $\rightarrow$ **`99.07%`** (`HuygensAdam`; `98.93%` w/ `CyclideAdam`, `98.53%` w/ `GyricAdam`)
-- **Held-Out Python AST Syntax Validity (`ast.parse`)**: `0.00%` $\rightarrow$ **`91.67%`** (`HuygensAdam`; `83.33%` w/ `CyclideAdam`)
-- **Held-Out Structured Tool-Call Token Top-1 Accuracy**: `36.44%` $\rightarrow$ **`90.69%`** (`HuygensAdam` & `PairAdam`; `89.50%` w/ `CyclideAdam`)
-- **Held-Out JSON Tool-Call Schema Match Rate**: `0.00%` $\rightarrow$ **`83.33%`** (`HuygensAdam` & `PairAdam`; `75.00%` w/ `CyclideAdam`, `GyricAdam`, `HuygensSymplecticAdam`)
-- **Code Signature/Docstring Conditioning Margin ($\Delta\mathcal{L}$)**: `0.8998` $\rightarrow$ **`1.6597` nats/tok** (`PairAdam`) / **`1.5766` nats/tok** (`SymplecticAdam`)
+- **Held-Out Code & Tool-Call Validation Perplexity**: `54.93` (`val_loss = 4.0061` base) → **`1.7632`** (`val_loss = 0.5672` w/ `HuygensAdam`; `1.8253` w/ `PairAdam`, `1.8619` w/ `GyricAdam`)
+- **Held-Out Python Code Token Top-1 Accuracy**: `46.80%` → **`99.07%`** (`HuygensAdam`; `98.93%` w/ `CyclideAdam`, `98.53%` w/ `GyricAdam`)
+- **Held-Out Python AST Syntax Validity (`ast.parse`)**: `0.00%` → **`91.67%`** (`HuygensAdam`; `83.33%` w/ `CyclideAdam`)
+- **Held-Out Structured Tool-Call Token Top-1 Accuracy**: `36.44%` → **`90.69%`** (`HuygensAdam` & `PairAdam`; `89.50%` w/ `CyclideAdam`)
+- **Held-Out JSON Tool-Call Schema Match Rate**: `0.00%` → **`83.33%`** (`HuygensAdam` & `PairAdam`; `75.00%` w/ `CyclideAdam`, `GyricAdam`, `HuygensSymplecticAdam`)
+- **Code Signature/Docstring Conditioning Margin (`ΔL`)**: `0.8998` → **`1.6597` nats/tok** (`PairAdam`) / **`1.5766` nats/tok** (`SymplecticAdam`)
 
 ---
 
@@ -38,7 +38,7 @@ It specializes the 12-layer Givens Rotational Transformer backbone for:
 
 We benchmarked all 8 classical geometric, Riemannian, conic, symplectic, gyroscopic, and synchronization optimizers from `transformers.models.grt.optimization_grt` on `MatterWaveAI/grt-30m-code` (`200` SFT steps on `blocks[11:12]` + `final_norm` + `<|im_end|>` polar phase calibration, `811,907` trainable parameters, `batch_size = 16`, `lr = 6.5e-3`, `max_angular_step = 0.12`, `seed = 42`):
 
-| Rank | Optimizer (`optimizer_type`) | Final Train Loss | Val Loss | Val PPL | Code Token Acc (%) | Tool-Call Token Acc (%) | JSON Schema Match (%) | Python AST Valid (%) | Conditioning Margin ($\Delta\mathcal{L}$) | Wall Time (s) |
+| Rank | Optimizer (`optimizer_type`) | Final Train Loss | Val Loss | Val PPL | Code Token Acc (%) | Tool-Call Token Acc (%) | JSON Schema Match (%) | Python AST Valid (%) | Conditioning Margin (`ΔL`) | Wall Time (s) |
 | :---: | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 | **1** | **`HuygensAdam` (`huygens_adam`)** | **`1.0882`** | **`0.5672`** | **`1.7632`** | **`99.07%`** | **`90.69%`** | **`83.33%`** | **`91.67%`** | `1.5152` | `138.63s` |
 | **2** | **`PairAdam` (`pair_adam`)** | `1.0994` | `0.6018` | `1.8253` | `97.60%` | **`90.69%`** | **`83.33%`** | `50.00%` | **`1.6597`** | `278.80s` |