apache / apache/geaflow

[geaflow/ai-memory] Define provenance model for facts, chunks, and evidence

Open
#842 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Java
Stars
808
Forks
188
Avg merge
3d 22h
Merged PRs (30d)
2

Description

Priority: P0
Difficulty: Starter

Context: Citation-aware answers and deletion propagation require source lineage. Existing subgraph verbalization does not provide claim-level provenance.

Scope:

- Add `ProvenanceRef` and `SourceSpan` contracts.
- Link extracted facts to document, chunk, extractor version, and schema version.
- Add JSON examples.

Constraints:

- Do not implement answer generation.
- Do not store full raw private text inside provenance objects.

Acceptance Criteria:

- Every extracted fact fixture can point back to source document and chunk.
- Missing provenance fails validation for extracted facts.

Suggested paths:

- `geaflow-ai/src/main/java/org/apache/geaflow/ai/provenance`

Contributor guide

Open the contributing guide

Research direction

Start in geaflow-ai/src/main/java/org/apache/geaflow/ai/provenance and review the existing extracted-fact fixtures and subgraph verbalization context. Define the ProvenanceRef and SourceSpan contracts, add JSON examples, and verify that each fact links to its document and chunk while missing provenance fails validation.

Written by the indexing model from the issue text.

Assessment

Tech stack
java
Domain
ai, data
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
66/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.