LLM Safety Evaluation Suite v1
Certified synthetic dataset for safety evaluation harness in ai-safety.
- Hash
- 43b160fac6…67d08b20
- Algorithm
- transformer
- Rows
- 0
A public index of registered AI model artifacts with cryptographic provenance records. Certified entries include Ed25519 signatures and SHA-256 fingerprints enabling independent integrity verification.
AI model artifacts include trained model weights, serialized checkpoints, and packaged inference containers. Certifying a model artifact creates a tamper-evident record proving the model binary existed at a specific timestamp and has not changed since. This supports EU AI Act compliance, governance audits, and reproducibility requirements.
Each certified entry in this category has an Ed25519-signed certificate record and a SHA-256 artifact fingerprint. Independent verification is possible without trusting CertifiedData directly.
Certified synthetic dataset for safety evaluation harness in ai-safety.
Certified synthetic dataset for fraud classification model in finance.
Submit an artifact via the API or dashboard. Once certified, it receives an Ed25519-signed certificate and appears in this registry with a live verification link.