---
title: "Provenance"
type: "glossary-term"
category: "Knowledge graph"
canonical_url: "https://www.graphcanon.com/glossary/knowledge-graph/provenance"
updated: "2026-07-09"
---

# Provenance

**Provenance is the recorded origin of a piece of data - where it came from, how it was derived, and when - so a claim can be traced and trusted.**

**Provenance** answers "says who, from what, and when?". For every fact or edge, it records the source (for example the GitHub API), the method used to derive it, and a timestamp.

Provenance is what separates a sourced signal from an opinion. It lets a reader - human or agent - audit a claim rather than take it on faith.

## In GraphCanon

Each typed edge and trust signal stores its provenance and a computed-at date. Trust reports name their methodology version and exactly what data was inspected.

## See also

- [How trust signals work](/trust-methodology)

## Related terms

- [Typed edge](/glossary/knowledge-graph/typed-edge.md)
- [Trust signal](/glossary/trust-and-signals/trust-signal.md)

[Knowledge graph](/glossary/knowledge-graph.md) · [All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_