ArcFlow
Company
Managed Services
Markets
  • News
  • LOG IN
  • GET STARTED

OZ brings Visual Intelligence to physical venues, a managed edge layer that lets real-world environments see, understand, and act in real time.

Talk to us

ArcFlow

  • World Models
  • Sensors

Managed Services

  • OZ VI Venue 1
  • Case Studies

Markets

  • Sports
  • Broadcasting
  • Robotics

Company

  • About
  • Technology
  • Careers
  • Contact

Ready to see it live?

Talk to the OZ team about deploying at your venues, from a single pilot match to a full regional rollout.

Schedule a deployment review

© 2026 OZ. All rights reserved.

LinkedIn
ArcFlow Docs
Get Started
  • Get Started
  • Quickstart
  • Installation
  • Project Setup
  • Platforms
  • Bindings
  • Licensing
  • Pricing
Capabilities
  • Vector Search
  • Graph Algorithms
  • Sync
  • MCP Server (AI Agents)
  • Live Queries
  • Programs
  • Temporal
  • Spatial
  • Trusted RAG
  • Behavior Graph
  • Agent-Native
  • Event Sourcing
  • GPU Acceleration
  • Intent Relay
Concepts
  • World Model
  • Graph Model
  • Query Language (GQL)
  • Graph Patterns
  • SQL vs GQL
  • Parameters
  • Query Results
  • Persistence & WAL
  • Error Handling
  • Observations & Evidence
  • Confidence & Provenance
  • Proof Artifacts & Gates
  • Skills
GQL / WorldCypher
  • Overview
  • MATCH
  • WHERE
  • RETURN
  • OPTIONAL MATCH
  • CREATE
  • SET
  • MERGE
  • DELETE
  • REMOVE
  • WITH
  • UNION
  • UNWIND
  • CASE
  • Spatial Queries
  • Temporal Queries
  • Algorithms Reference
  • Triggers
Schema
  • Overview
  • Indexes
  • Constraints
  • Data Types
Functions
  • Built-in Functions
  • Aggregations
  • Procedures
  • Shortest Path
  • EXPLAIN
  • PROFILE
Skills
  • Overview
  • CREATE SKILL
  • PROCESS NODE
  • REPROCESS EDGES
Operations
  • CLI
  • REPL Commands
  • Snapshot & Restore
  • Server Modes & PG Wire
  • Persistence
  • Import & Export
  • Docker
  • Architecture
  • Cloud Architecture
  • Sync Protocol (Deep Dive)
Guides
  • Agent Integration
  • World Model
  • Graph Model Fundamentals
  • Trusted RAG
  • Using Skills
  • Behavior Graphs
  • Swarm & Multi-Agent
  • Migration Guide
  • Filesystem Workspace
  • From SQL to GQL
  • ArcFlow for Coding Agents
  • Data Quality & Pipeline Integrity
  • Code Intelligence
Tutorials
  • Knowledge Graph
  • Entity Linking
  • Vector Search
  • Graph Algorithms
Recipes
  • CRUD
  • Multi-MATCH
  • MERGE (Upsert)
  • Full-Text Search
  • Temporal Queries
  • Batch Projection
  • GraphRAG
Use Cases
  • Agent Tooling
  • Knowledge Management
  • RAG Pipeline
  • Fraud Detection
  • Sports Analytics
  • Grounded Neural Objects
  • Behavior Graphs
  • Autonomous Systems
  • Digital Twins
  • Robotics & Perception
Reference
  • TypeScript API
  • GQL Conformance
  • Compatibility Matrix
  • Glossary
  • Data Types
  • Operators
  • Error Codes
  • Known Issues

Confidence & Provenance

The ArcFlow Evidence Model makes every fact in the world model epistemically graded. Every node and relationship carries an observation class, a confidence score, and a provenance chain — built into the storage engine, not bolted on.

Query r._confidence, r._skill_version, or r._created_at on any relationship the same way you query r.weight or r.type. This isn't optional metadata — it's how ArcFlow stores edges.


Confidence Score#

Every edge carries _confidence — a float from 0.0 to 1.0 indicating how reliable the data is.

ValueMeaning
1.0Manually asserted or directly measured
0.75+High confidence — default skill materialization threshold
0.5–0.75Medium — may need re-evaluation as evidence improves
< 0.5Low — candidate for REPROCESS EDGES

Static edges (manually created with CREATE or MERGE) default to confidence 1.0. Dynamic edges (produced by Skills) carry the full provenance chain.


Edge Provenance#

Every dynamic edge carries:

PropertyDescription
_skill_versionWhich skill version built this edge
_model_fingerprintThe model or extractor that produced the source data
_provenance_hashHash of the full provenance lineage
_created_atTimestamp of materialization

These are queryable directly:

MATCH (a:Robot)-[r:ZONE_PEER]->(b:Robot)
RETURN
  a.name, b.name,
  r._confidence,
  r._skill_version,
  r._created_at
ORDER BY r._confidence DESC

Confidence-Weighted Traversal#

Confidence propagates multiplicatively along paths. A path through two 0.9-confidence edges has path confidence 0.81. This means longer inference chains naturally accumulate uncertainty — queries can filter on path-level confidence rather than edge-level alone.


Filtering by Trust#

-- High-trust sensor detections only
MATCH (s:Sensor)-[d:DETECTED]->(r:Robot)
WHERE d._confidence > 0.85
RETURN s.name, r.name, d._confidence
 
-- Identify edges needing re-evaluation
MATCH ()-[r]->()
WHERE r._confidence < 0.6
RETURN type(r), r._skill_version, r._confidence
ORDER BY r._confidence
 
-- Re-run skills against stale low-confidence edges
REPROCESS EDGES WHERE confidence < 0.6

Observation Class + Confidence Together#

Observation class and confidence work as a two-axis trust model:

Observation ClassConfidenceInterpretation
observed0.95Direct high-quality sensor reading — authoritative
observed0.62Direct but degraded reading — sensor occlusion, noise
inferred0.88Strong algorithmic derivation — reliable
inferred0.51Weak derivation — needs corroboration
predictedanyModel output — use for planning, not for facts

A query that needs authoritative facts filters on both:

MATCH (r:Robot)
WHERE r._observation_class = 'observed'
  AND r._confidence > 0.85
RETURN r.name, r.x, r.y, r._confidence

See Also#

  • Observations & Evidence — observation classes and the ArcFlow Evidence Model
  • Skills — how skills produce confidence-scored edges with provenance
  • REPROCESS EDGES — re-evaluating low-confidence edges
  • Trusted RAG — confidence-filtered retrieval from the world model
  • Proof Artifacts & Gates — cryptographic state proofs built from the evidence chain
Try it
Open ↗⌘↵ to run
Loading engine…
← PreviousObservations & EvidenceNext →Proof Artifacts & Gates