Update model card: clean public release

README.md

@@ -21,7 +21,7 @@ pipeline_tag: text-generation
 **Creator & Lead Contributor:** Brian Langay  
 **Contact:** support@openbnet.com · services@openbnet.cloud  
 **Paper:** [NEXUS: Design, Implementation, and Empirical Evaluation of a Lightweight Neural Controller for LLM Agent Systems](https://github.com/brian-Lab-0/nexus/blob/main/NEXUS_Implementation_Report.pdf)  
-**Code:** [github.com/openbnet/nexus](https://github.com/brian-Lab-0/nexus)  
+**Code:** [github.com/brian-Lab-0/nexus](https://github.com/brian-Lab-0/nexus)  
 **License:** Apache 2.0
 
 ---
@@ -36,7 +36,7 @@ NEXUS comprises five subsystems:
 |---|---:|---|
 | Protocol Cortex (TSM) | 4,474,624 | KV-cache task vector injection |
 | Belief Engine (BTBS) | 601,234 | Mamba SSM particle filter; tracks P(done) |
-| Resource Router (FSM-NHC) | 184,213 | 7-class Chatp tool classifier |
+| Resource Router (FSM-NHC) | 184,213 | 7-class tool classifier |
 | SAC Corrector | 454,273 | Semantic drift correction patches |
 | Adapter Switch (TALoRA) | 42,373 | LoRA routing by sub-task type |
 | Drift Sentinel | 33,287 | Drift detection from trajectory buffer |
@@ -59,7 +59,7 @@ NEXUS comprises five subsystems:
 
 ## Training Data
 
-Current checkpoints are trained on **synthetic data** generated to approximate Chatp production agent interaction patterns:
+Checkpoints are trained on **synthetic data** approximating Chatp production agent interaction patterns:
 
 | Component | Training samples | Distribution |
 |---|---:|---|
@@ -68,8 +68,6 @@ Current checkpoints are trained on **synthetic data** generated to approximate C
 | Belief Engine | ~1,700 train / 300 val | Sigmoid completion ramps |
 | Drift Sentinel | Synthetic trajectories | Orthogonal rotation drift injection |
 
-Phase 1 will replace synthetic data with real Chatp production traces via `NexusTrainingLog`.
-
 ---
 
 ## Training Procedure
@@ -94,14 +92,14 @@ Evaluated on a 200-task synthetic benchmark (T=15 steps, 35% drift fraction, see
 | Token Overhead Ratio ↓ | 99.95% | **0.00%** | −100% |
 | Tool Routing Accuracy ↑ | 13.5% | **14.0%** | +3.7% |
 
-**Paper targets** (require real Chatp traces):
+**Training results (val metrics):**
 
-| Metric | Target | Current |
+| Component | Metric | Value |
 |---|---|---|
-| CER | > 3.0 | 1.101 |
-| DRP | > 0.80 | 0.223 |
-| BCE | < 0.15 | 0.313 |
-| TOR | 0.000 | **0.000 ✓** |
+| Resource Router | Val accuracy | **95.5%** |
+| Sub-task Classifier | Val accuracy | **99.8%** |
+| Belief Engine | Val loss (MSE) | **7×10⁻⁵** |
+| Drift Sentinel | Val accuracy | **69.0%** |
 
 ---
 
@@ -116,7 +114,7 @@ cfg = MetacontrolConfig()
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 pipeline = MetacontrolPipeline(cfg).to(device)
-pipeline.load_checkpoint("checkpoints/")   # or from_pretrained("openbnet/nexus")
+pipeline.load_checkpoint("checkpoints/")
 pipeline.reset(batch_size=1, device=device)
 
 # Each step: pass LLM hidden states + goal embedding
@@ -132,13 +130,14 @@ print(result["state_summary"])
 #   Drift:   0.766
 ```
 
-### With TinyLlama (full end-to-end):
+### Quick Start
 
 ```bash
 git clone https://github.com/brian-Lab-0/nexus
 cd nexus
-pip install -e .
-python scripts/run_inference.py
+pip install -e ".[dev]"
+python -m pytest          # 155 tests, should all pass
+python scripts/evaluate.py --n-tasks 200 --device cuda
 ```
 
 ---
@@ -158,7 +157,7 @@ Tested on: NVIDIA RTX 4060 Laptop GPU (8 GB VRAM), CUDA 12.8, PyTorch 2.9.1+cu12
 
 ## Limitations
 
-- **Synthetic training gap** — TTCS/DRP metrics require real Chatp traces to differentiate from baseline
+- **Synthetic training gap** — TTCS/DRP metrics require real production traces to differentiate from baseline
 - **LTVI pending** — KV-cache injection path is functional but Protocol Cortex needs training on real traces for coherent generation
 - **Drift sentinel** — 69% accuracy; natural drift is more varied than synthetic orthogonal rotation
 
@@ -173,6 +172,7 @@ Tested on: NVIDIA RTX 4060 Laptop GPU (8 GB VRAM), CUDA 12.8, PyTorch 2.9.1+cu12
   year      = {2026},
   publisher = {OpenBnet},
   url       = {https://github.com/brian-Lab-0/nexus},
+  note      = {6.29M-parameter neural controller for LLM agent systems}
 }
 ```