core · verifiable knowledge

From information to verifiable knowledge.

Structured evidence becomes a governed knowledge base — canonicalized, deduplicated, versioned and evidence-linked, with lineage and citations down to the source. Served to people, agents and any model via API and MCP.

provenancelineagecitationsversionsknowledge graphdedupAPI + MCPmodel-agnostic
GET /v1/knowledge/objects/kn_842
# a knowledge object — not text
GET /v1/knowledge/objects/kn_842

# 200 OK
{ "claim": "Contract renewal date moved to 2026-09-01",
  "state": "SUPPORTED", "version": 4,
  "evidence": 3, "contradictions": 1, "relationships": 21,
  "lineage": "amendment_v2.pdf · page 4 · bbox",
  "abstains_when": "insufficient_evidence" }
The problem

AI stacks store conclusions and discard the proof.

Ad-hoc chunks, lossy markdown, orphan embeddings, answers with invisible foundations. Six months later nobody can say where a fact came from, whether it is still true, or what changed when it did. Knowledge becomes disposable — and unprovable.

no provenanceunreproducible indexesinvisible foundationssilent driftconfident hallucination
What it produces

A knowledge base that carries its own proof.

Knowledge objects

Claims with evidence, contradictions, relationships, versions and resolution states — not text. Insufficient evidence means ABSTAINED, never a guess.

Lineage and citations

Every fact traces to its exact source position — page, bounding box, timestamp — through a deterministic, reconstructible canonical substrate. When a defect is found, you can replay and prove exactly what changed.

Served everywhere

APIs and MCP for agents, LLMs, applications and people — plus a native experience, the Orves Console (pilot): ask, explore the graph, compare versions, and drill from any answer to its evidence. Swap the model, keep the knowledge.

How it works

Three moves. Nothing hidden.

01

Connect

Point it at certified parses — or at your sources and let the pipeline run end to end.

02

Adjudicate

Conflicting evidence is compared, deduplicated, versioned and resolved. Every change creates a new version; nothing is ever overwritten.

03

Serve

People, agents and any model consume knowledge objects with grounding, citations, abstentions and a certificate.

Inside the product

From evidence to knowledge, stage by stage.

Each stage is measured, versioned and deterministic — change enters through the flow, never by edit.

Structured evidencecertified parses in — spans, geometry, provenance
Canonicalizationdeterministic substrate — reconstructible, byte-stable
Deduplicationthe same fact once — sources merged, none lost
Claim extractiontyped claims, each with its evidence attached
Adjudicationsupport vs contradiction — resolved, or ABSTAINED
Versioningevery change is a new version; nothing overwritten
Knowledge objectsclaims + evidence + relationships + history
ServedAPIs · MCP — people, agents, any model

Where this engine sits in the platform → architecture

Show me

Anatomy of a knowledge object.

Not text — a governed object. Every part below is addressable through the API.

KNOWLEDGE OBJECT · kn_842 · v4
“Contract renewal date moved to 2026-09-01.”
SUPPORTED
Evidence · 3 supporting · 1 contradicting
amendment_v2.pdf · p.4 ¶3supporting
renewal_notice.eml · 2026-06-12supporting
board_minutes.pdf · p.2supporting
contract_2024.pdf · p.12contradicting · superseded
Relationships · 21
renews → Contract #442
party → Supplier XYZ
affects → Invoice #9812
+ 18 more
History
v1 · Jun · scheduled Jun 30
v2 · Jul · postponed
v3 · Aug · new date proposed
v4 · Sep · moved to Sep 1current
Certificate
cert_9f2… · kb@2026.07verify ✓
party claims supplies bills Acme Corp Contract #442 kn_842 · renewal Supplier XYZ Invoice #9812 the same object, inside the knowledge graph
History

Watch a claim live.

New evidence arrives; the claim is re-adjudicated; a new version is written. Nothing is ever overwritten — every state keeps its evidence.

JUNv1

Renewal scheduled for Jun 30

contract_2024.pdf · p.12
JULv2

Renewal postponed

renewal_notice.eml
AUGv3

New date proposed: Aug 15

draft_amendment.pdf · p.2
SEPv4

Renewal moved to Sep 1

amendment_v2.pdf · p.4

The object above is v4 of this claim — same asset, full history attached.

Before × after

Retrieval finds text. The layer preserves why it is true.

Traditional RAG

  • PDF
  • chunks
  • embeddings
  • top-k
  • LLM
  • answer — origin unknown

When the answer is wrong, there is nothing to inspect.

On Verifiable Knowledge

  • PDF
  • structured evidence
  • knowledge objects
  • versions + grounding
  • LLM
  • answer — traceable to the page

When the answer is challenged, you show why.

Model agnostic

One knowledge asset. Every model.

Models are interfaces — they change every quarter. Knowledge is the asset that compounds. Build it once, serve it to all of them, swap any of them tomorrow.

GPTClaudeGeminiLlamaMistralDeepSeekyour own model

Swap the model. Keep the knowledge.

Benchmarks

Measured before claimed.

Public benchmarks

Pre-registered evaluations against named competitors — published with the pilot, every number with its n.

Internal evaluation

Running today on proprietary gold sets. A number appears below only after it survives its gate — until then, the honest state is shown.

DimensionUnitStatusNotes
Determinismidentical re-runsmeasured · internalbyte-level round-trip checks
Reconstruction fidelityknowledge → sourcemeasured · internalpublication after pre-registered eval
Claim extractionprecision / recall vs goldmeasured · internalpublication after pre-registered eval
Abstention calibrationabstains when evidence is insufficientmeasured · internalUNKNOWN counted, never hidden
Grounding fidelityanswers traceable to claimsmeasured · internalmeasured on adversarial sets
Chunk boundary qualitystructure alignmentpublication pendinggold set in construction

A knowledge base that cannot show its grounding is measured as wrong — fluency does not count. Continuous benchmark →

Pricing

Credits per unit of work.

1 page canonicalizedunit
2 creditsdraft ratio
1 knowledge operation — ingest · update · retrieve · consolidateunit
5 creditsdraft ratio

Certificates included with every artifact. How pricing works →

A property, not a product

Every artifact is verifiable.

Certification runs through everything Orves produces. Anyone can verify a certificate — free, forever, no account.

✓ provenance✓ lineageversioningevidencegovernanceresolution statestrust →
API first

Integrate in minutes.

Everything is delivered through the API. Nothing to install, nothing to host.

REST APIPythonTypeScriptGoJavaOpenAPIExamplesPlayground soon
Questions

FAQ

What exactly am I buying?

A knowledge base where every fact carries origin, context, history, versions and evidence — queryable by people, agents and any model. Not a vector store, not a wiki, not a chatbot: an asset you can audit and prove.

Does it compete with GPT or Claude?

No — it feeds them. Models are interfaces; this is where your knowledge persists. Swap the model, keep the knowledge. We don't build AI — we build knowledge AI can trust.

Where did Canonical and Knowledge go?

They became capabilities of this product. Canonicalization is the mechanism that makes knowledge deterministic and reconstructible; the persistent memory layer is how it is served and accumulated. You buy the outcome — knowledge you can prove — not the internal stages.

Why aren't chunks and embeddings enough?

Chunks discard structure and context; embeddings discard provenance and history. Both keep what the text says and lose why it can be trusted — source, version, relationships, adjudication. Retrieval finds text; the layer preserves why it is true. RAG built on chunks cannot answer 'how do you know?' — knowledge objects can.

Why does determinism matter?

Because proof requires replay. When a defect is found, the canonical substrate lets you re-derive every downstream artifact and show exactly what changed — and what did not.

Does my knowledge stay current?

Yes, when you need it to. Continuous knowledge is a capability of the platform — approved sources are monitored, changes are detected, history is preserved and new versions are created. Knowledge is never overwritten, and provenance is maintained through every update. It runs as a recurring service — see the Living Knowledge solution.

Is my knowledge shared?

No. Each instance is isolated by construction and reasons only over your governed knowledge. Nothing you ingest trains shared models.

Is there an interface, or is it API-only?

Delivery is API-first, and the product includes a native experience — the Orves Console (pilot): question answering with evidence, graph exploration, version comparison and the Show-me-why drill-down from any answer to its source span. It is how you experience the product, not a fourth product.

Turn your documents into knowledge you can prove.

15,000 free credits · no credit card · knowledge APIs arrive with the pilot.