evidence-auditor

Evidence Auditor

Triggers & routing

Trigger: evidence audit, missing evidence, unsupported claims, review evidence audit, evidence gaps.
Use when: paper-review In the process, it is necessary to check the evidence chain of each claim, missing baselines, and weak points in evaluation one by one.
Skip if: missing claims input (for example, there is not yet output/CLAIMS.md）。
Network: none.
Guardrail: only write "gaps/risks/next-step verification"; do not write arguments on behalf of the authors or introduce new claims.

Transforms a claim ledger into a gap report for paper-review.

Input

output/CLAIMS.md

Output

output/MISSING_EVIDENCE.md
output/EVIDENCE_AUDIT.jsonl (review-evidence-gap.v1)

Contract

Each gap block should include:

claim reference
what evidence is already present
what is missing or weak
minimal fix
severity

Each JSONL record must retain claim_id and a stable gap_id so the final review can cite the exact failure rather than paraphrasing an unlocated concern.

Script boundary

scripts/run.py should:

iterate existing claims only
classify the likely evidence risk
write actionable, bounded gap items

It should not invent new claims or rewrite the manuscript.

Acceptance

every claim has a corresponding evidence note or gap item
minimal fixes are actionable and concrete
structured records join back to every claim_id

Non-goals

manuscript rewriting
novelty assessment
recommendation writing