VRI binds file integrity enforcement and knowledge traceability into a single enforceable layer. Two independently deployable components implement this stack. Integration is achieved at the artifact boundary.
Both components share a common cryptographic foundation in SHA-256 content addressing. They operate at different semantic layers.
Provenance engine. Cryptographic artifact anchoring with forensic change detection. Hardware-isolated signing.
Knowledge extraction engine. Claim-centric graph with source-sentence provenance. Sensitivity-gated retrieval.
Unified deployment. A claim is only valid if its source document is intact. A source document is only meaningful if its claims can be traced. Both conditions enforced at every point in the chain.
Three distinct trust zones govern data movement. Each boundary crossing is enforced by specific, named controls.
Both components are in active pre-SBIR development. This table characterizes current readiness so evaluators can calibrate.
| Component | Status | Scope |
|---|---|---|
| GraphRAG Ingest Pipeline | DEPLOYED | 109-document corpus, five extraction layers, production graph |
| GraphRAG Retrieval API | DEPLOYED | JWT auth, RBAC, sensitivity gating, rate limiting |
| Aletheia Core (Python) | FUNCTIONAL | SHA-256 anchoring, ALBC barcoding, software Ed25519 signing |
| Hardware Signing Oracle | FUNCTIONAL | Odin binary on RPi 5, AOKF key format, audit log, wire protocol |
| Aletheia ↔ GraphRAG Integration | P2 ROADMAP | Anchor source docs before extraction, artifact_id on Document nodes |
| Salience-Aware Retrieval | P1 ROADMAP | Conversation log weight updates, template re-ranking |
The system has been deployed against the Turnbull National Wildlife Refuge documentary archive. The corpus includes wildlife management reports, survey records, and habitat assessments. All documents were processed through the full ingest-to-retrieval pipeline.