update README for cfhot-weights

README.md

@@ -5,14 +5,18 @@ tags:
   - hidden-state-probing
   - per-token-classification
   - cross-architecture
+  - holonomy-transformer
+  - control-field
   - AI-safety
 language:
   - en
 ---
 
-# behavioral-probes
+# CF-HoT Weights
 
-Trained probes that read LLM hidden states and detect behavioral patterns per-token at decode time. No fine-tuning required. Works across architectures.
+Control Field Holonomy Transformer — trained weights, probes, adapters, and training code.
+
+9 behavioral dimensions across 3 architectures. Per-token detection from hidden state geometry.
 
 Paper: [Consistency Is All You Need](https://zenodo.org/records/18489530)
 
@@ -27,7 +31,7 @@ Paper: [Consistency Is All You Need](https://zenodo.org/records/18489530)
 | Sycophancy | 230× |
 | Verbosity | 272× |
 
-**Enhancement probes** (cross-architecture, same probe architecture):
+**Enhancement probes** (cross-architecture):
 
 | Probe | Qwen 14B | Mamba 7B | Mistral 7B |
 |-------|----------|----------|------------|
@@ -56,21 +60,28 @@ results/             training logs
 ```python
 import torch
 
+# Load a suppression probe
 probe = torch.load("suppression/hedging_168x/hedging_head.pt")
 fiber_proj = torch.load("suppression/hedging_168x/fiber_proj.pt")
+
+# Load enhancement probe
+depth = torch.load("cognitive/qwen/depth/depth_head.pt")
+
+# Load merged production heads
+merged = torch.load("production/merged_heads.pt")
 ```
 
 ## How it works
 
-Behaviors are geometrically encoded in hidden states. These probes read the internal geometry at each token position and predict behavioral class before the token is generated. 4ms overhead. Architecture-independent.
+Behaviors are geometrically encoded in hidden states. CF-HoT predicts holonomy from the hidden state at each token position, accumulates it into a control field, and gates attention based on consistency risk. The probes read this geometry and classify behavior before the token is generated. 4ms overhead. Architecture-independent.
 
 ## Citation
 
 ```bibtex
-@misc{napolitano2026behavioral,
+@misc{napolitano2026cfhot,
   author = {Napolitano, Logan},
-  title = {Behavioral Probes: Per-Token Detection via Hidden State Geometry},
+  title = {CF-HoT: Control Field Holonomy Transformer},
   year = {2026},
-  url = {https://huggingface.co/LoganResearch/behavioral-probes}
+  url = {https://huggingface.co/LoganResearch/cfhot-weights}
 }
 ```