Formal verification framework for dataset lineage, policy compliance, and training-time safety guarantees.
-
Updated
Jul 16, 2026 - Python
Formal verification framework for dataset lineage, policy compliance, and training-time safety guarantees.
Safety-aware training and evaluation platform for sequential policies and frontier LLMs under a deterministic policy gate and strict verifier.
Source, reproduction, and validation for the Bonsai-27B Heretic GGUF LoRA and standalone merge.
Add a description, image, and links to the model-safety topic page so that developers can more easily learn about it.
To associate your repository with the model-safety topic, visit your repo's landing page and select "manage topics."