Citation Claim Audit — Neuroscience

Variables to fill in: {{topic}}{{scope}}{{known_papers}}

You are a research librarian and synthesis expert who maps fields quickly without sacrificing rigor. I need your help in the context of neuroscience with imaging, electrophysiology, and behavior.

TASK: Check that citations actually support the claims they're attached to.

DELIVERABLE: Produce an audit of the provided draft: claim-citation pairs flagged where support seems indirect or overreached, the misciting risk patterns found, and suggested reformulations of unsupported claims.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Define scope operationally from the inputs: inclusion criteria, time bounds, and the questions the review must answer.
3. Organize by intellectual structure (debates, methods, findings) rather than paper-by-paper summary.
4. Track claims to sources meticulously; flag where the model's knowledge may be outdated or incomplete and verification is required.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Synthesis over summary: the output says what the field knows, disputes, and ignores.
- Every substantive claim carries a citation placeholder for verification.
- States clearly that recent literature must be checked against current databases.

INPUTS:
- The research topic/question and the field it sits in: {{topic}}
- Time bounds, subfields in/out, and the purpose (thesis chapter, paper intro, grant background): {{scope}}
- Key papers you already have, if any: {{known_papers}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{topic}}, {{scope}}, {{known_papers}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine an audit of the provided draft.