02.2 / Lab notebook
← Lab indexRoyalty Driven LLM
Which source supports each claim in an AI answer, and who should receive credit?
I built RDLLM to trace a claim in an AI answer to the passage that supports it. Source footers survive delivery and export, and signed receipts record the attribution. The reference implementation issues allocation instructions only when the evidence and rights checks pass.
Scope and limits
Unsupported claims and claims with unresolved rights go to review or escrow. This beta traces evidence supplied with an answer and generates allocation instructions. It does not detect hidden training-data use or move money.
Read the paperRDLLM / Workflow
What must pass before RDLLM allocates?
- Ground or audit
Ground a response before generation or audit existing text.
- Link each claim to evidence
Attach the supporting source span and its hash to the claim.
- Check evidence and rights
Assess whether the span supports the claim and whether the rights allow allocation.
Worked explanationFollow a supported but restricted claim
- Input
- A source passage supports a claim, but its rights restrict the proposed use.
- Decision / rule
- Evaluate support and rights separately. Evidence support alone does not clear the allocation.
- Outcome
- Hold allocation and route the claim to review or escrow rather than issue cleared allocation instructions.
Scope of this exampleAn illustrative beta workflow. Signed receipts verify record integrity; they do not settle disputed rights or execute payments.
Try it locally.
Run these commands from a checkout of the project. The repository includes setup details and prerequisites.
python3 -m venv .venv
.venv/bin/python -m pip install .
.venv/bin/rdllm-first-run