Add method figure and checkpoint architecture description

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/Method.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -8,7 +8,43 @@ tags:
 
 Trained Sigma-Mem parameters for five center-model configurations.
 
-| Checkpoint directory | Center model |
+![Sigma-Mem method overview](assets/Method.png)
+
+## What These Checkpoints Contain
+
+These files contain the **Sigma-Mem components** illustrated in the figure above;
+they do not contain a fine-tuned copy of the Central Model (CM). For each peer
+\(p\), Sigma-Mem maintains a real symmetric memory matrix
+\(\mathbf{M}_p \in \mathbb{R}^{r \times r}\), with
+\(\mathbf{M}_p = \mathbf{M}_p^\top\). Given the current task direction
+\(\boldsymbol{\phi}(\mathbf{x}_t)\), the memory readout is
+
+\[
+\mathbf{r}_{p,t} = \mathbf{M}_p\boldsymbol{\phi}(\mathbf{x}_t),
+\]
+
+and the learned projection converts this readout into a peer-specific residual
+steering vector:
+
+\[
+\boldsymbol{\delta}_{p,t}
+= g\,\mathbf{P}\mathbf{M}_p\boldsymbol{\phi}(\mathbf{x}_t).
+\]
+
+The steering vector is added only to the upper residual stream while the CM judges
+peer \(p\)'s response. It therefore influences response aggregation through the
+CM's Yes-versus-No utility scores, while all original CM parameters remain frozen
+and unchanged. The joint relationship matrix \(\mathbf{G}\) is updated separately
+from peer correctness patterns and is used by the final peer-selection posterior.
+
+Each checkpoint provides the learned Sigma-Mem address/projection and residual-
+steering parameters needed by this process. Runtime \(\mathbf{M}_p\) and
+\(\mathbf{G}\) states are initialized for the evaluation stream and updated only
+after the current decision receives external correctness feedback.
+
+## Available Checkpoints
+
+| Checkpoint directory | Frozen center model |
 | --- | --- |
 | `Qwen3-0.6B` | Qwen3-0.6B |
 | `Qwen3-4B` | Qwen3-4B |