Questions, answered plainly.
Do I have to adopt the whole platform?
No. Parser stands alone; most teams land there and add Verifiable Knowledge when they need knowledge they can trust and prove. The Living Knowledge solution — continuous monitoring — is the natural next step when that knowledge changes often.
Does Orves lock me into its intelligence?
The opposite. Verifiable Knowledge ends in an asset you own — model-ready for GPT, Claude, Gemini or your own model: retrieval, fine-tuning, training data. Being served by Orves APIs is a choice, never a requirement.
What happened to Canonical, Knowledge and the Knowledge Engine?
They are inside Verifiable Knowledge, not on the price list. Canonicalization makes knowledge deterministic and reconstructible; the Knowledge Engine governs claims, evidence and versions. You buy the outcome — knowledge you can prove. Certification remains a property of everything Orves produces.
What do you mean by “verifiable”?
Every transformation emits a certificate recorded on an immutable ledger. Anyone can verify a certificate — free, without an account. Claims ship with evidence and resolution states.
What is a canonical substrate?
One representation per source — versioned, deterministic, reconstructible, with permanent IDs and provenance to the span. Everything downstream (chunks, datasets, indexes, answers) is a projection that can be re-derived and proven equivalent.
Where do benchmark numbers come from?
From pre-registered evaluations against versioned gold sets, with n and confusion matrices reported. A number appears on this site only after it survives that process — until then you see the honest state.
How is Orves delivered?
Exclusively through the API. Nothing to install, nothing to host. Thin SDKs are provided for convenience — the platform lives server-side.
Is Orves a RAG stack?
No. RAG is one possible projection of the canonical substrate. Orves governs the layer that RAG stacks improvise.