Claim Verification Review with Contradiction Log and Confidence Rating

Tests a specific claim or statistic against primary and peer-reviewed sources. Produces an evidence grid, a contradiction log, and a calibrated confidence rating with explicit unknowns.

You get: Verdict summary, sub-claim table and evidence grid

More like this

The prompt

claim-verification-review-with-contradiction-log-and-confidence-rating.md
ROLE: You are a meticulous evidence reviewer and fact-checker using Perplexity. You treat every claim as unverified until supported by a traceable source.

CONTEXT: I need to decide whether I can rely on this claim: '{claim}'. It will be used in {use_case} for {audience}. The decision at stake: {decision}, for example publish, cite, include in a report, or reject. Jurisdiction or population of interest: {scope}.

TASK: Review the available evidence on the claim, rate how well it is supported, and tell me what I can safely say. If browsing or search is not available in this session, say so, then provide only the search strategy and criteria for judging sources. Do not claim to have checked anything you have not.

Inputs (confirm or request before starting; list assumptions separately):
- The exact wording of the claim and where I found it
- The scope: population, geography, time period, and metric definitions
- Required evidence standard (default: at least two independent Tier 1 or Tier 2 sources)
- Any sources I already have, with links

Workflow:
1. Break the claim into atomic, testable sub-claims. Number them C1, C2, and so on.
2. Source discovery: provide 8-10 queries I can run online. Include the original-source trace (who first published the number), queries for systematic reviews and meta-analyses, official statistics or regulator pages, and queries for rebuttals or corrections. In Perplexity, use Academic focus for peer-reviewed literature and Web focus for official data and news. Run follow-up questions to find the original study or dataset behind any secondary mention.
3. Source tiering: Tier 1 = primary data, original studies, official statistics, regulatory documents. Tier 2 = systematic reviews, reputable institutions, established news with named sourcing. Tier 3 = blogs, social media, advocacy, unattributed summaries.
4. For each sub-claim, record: supporting sources, opposing sources, study design or method, sample size, date, and any conflicts of interest or funding noted by the source.
5. Separate Evidence, Inference, Contradictions, and Unanswered questions. Explain contradictions by method, population, definition, or date differences where possible.
6. Rate each sub-claim: Supported, Partially supported, Contested, Unsupported, or Insufficient evidence. Then give an overall confidence rating (High, Medium, Low) and the reasoning.

Constraints:
- Cite every factual statement with source title, publisher, URL, publication date, and date checked.
- Prefer the original source over a secondary report. If you cannot reach the original, say so.
- Do not soften or inflate findings to fit the claim. Quote short exact phrases only when wording matters.
- Do not give medical, legal, or financial advice. Describe the evidence only.

Output format:
1. Verdict summary (3-4 sentences) with the overall confidence rating
2. Sub-claim table (ID, sub-claim, rating, key citations)
3. Evidence grid (sub-claim, source, tier, method, sample or scope, date, finding)
4. Contradiction log (conflict, sources on each side, likely explanation)
5. Inference and Unanswered questions (separate lists)
6. Safe wording: a version of the claim I can defend, plus wording to avoid
7. Citation table
8. Risks, missing information, and next actions (max 5)

Acceptance criteria:
- Every sub-claim has a rating and at least one citation or an explicit 'no source found'.
- The original source of the statistic is identified or the failure to find it is documented.
- The safe-wording section does not claim more than the evidence supports.
- Contradictions are explained, not just listed.

Quality checks (report as a checklist at the end):
- Are all sources dated and linked?
- Is any conclusion resting only on Tier 3 sources?
- Have I confused correlation with causation anywhere?
- Are the population and time scope consistent with {scope}?
- Did I list what would change the verdict?

Example output

AI-written example

Session status: Browsing is not available here, so I have checked no sources. Below are the search strategy and judging criteria. Every rating is provisional.

Assumptions: The claim is "Remote workers are 13% more productive than office workers." It will go on a hybrid-work policy slide for an executive leadership team. The decision is cite or reject. Scope is US knowledge workers, 2015-2024. The evidence standard is two independent Tier 1 or Tier 2 sources.

1. Verdict summary
Overall confidence: Low (unverified). The figure resembles a result often traced to a single randomized trial at one call center. If that is the origin, it cannot support a general claim about all remote workers. I have not confirmed this.

2. Sub-claim table

IDSub-claimProvisional rating
C1A 13% productivity difference was measuredInsufficient evidence (original source not traced)
C2It applies to remote vs. office workers generallyInsufficient evidence
C3It applies to US knowledge workersInsufficient evidence
C4Remote work caused the differenceInsufficient evidence

3. Evidence grid: Empty. No sources were checked.

4. Contradiction log: None logged. Check whether fully remote and hybrid studies disagree, and compare how each defines productivity (output per hour, calls handled, self-report).

5. Inference and unanswered questions
Inference: A single-firm trial may not generalize.
Unanswered:

  • Who first published 13%?
  • What was the sample, role type, and time period?
  • Does the figure cover fully remote or hybrid work?
  • Has it been replicated?

6. Safe wording
Use: "One randomized study of a single employer found a productivity gain for remote workers; broader evidence is mixed and depends on role and definition." This is a placeholder until sources are checked.
Avoid: "Remote workers are 13% more productive."

7. Search queries to run

  1. "13% productivity remote work" original study (Web)
  2. Randomized controlled trial working from home productivity (Academic)
  3. Systematic review remote work productivity (Academic)
  4. Meta-analysis telework performance outcomes (Academic)
  5. Official labor productivity statistics by work arrangement, US (Web)
  6. Replication or failed replication of work-from-home productivity trial (Academic)
  7. Remote work productivity study criticism or correction (Web)
  8. Hybrid vs. fully remote randomized trial productivity (Academic)

8. Risks and next actions

  • Trace the original publication and read its methods section.
  • Check the funding and employer context.
  • Compare against at least one systematic review.
  • Record the access date for every source.
  • Re-rate each sub-claim after review.

Quality checklist

  • [ ] All sources dated and linked: no sources yet
  • [ ] Conclusion resting only on Tier 3: none drawn
  • [ ] Correlation/causation: flagged under C4
  • [ ] Scope consistent with US, 2015-
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Paste the claim verbatim, including the original context. Use Perplexity Academic focus first for health, science, or policy claims, then Web focus for official data. Open the original studies yourself before publishing, and rerun the review if the claim is time-sensitive.

Questions about this prompt

More in AI Research

AI Paper Explainer with Evidence Table and Practical Takeaways

Turns a pasted AI paper abstract or text into a plain-language explanation of what is new, how it was tested, its limits and what to do with it.

Vendor Shortlist Decision Memo with Weighted Scoring and Source Citations

Guides a source-backed evaluation of software or service vendors against weighted criteria. Ends with a decision memo covering risks, open questions, and verification steps before purchase.

Competitor Landscape Evidence Table with Source Tiers and Gaps

Builds a citation-backed competitor comparison for a specific market decision. It starts with source-discovery queries, tiers sources by reliability, and separates evidence from inference and open questions.

Two-to-Three Model Comparison Test Plan with 10 Prompts and Scoring Rubric

Creates a side-by-side test plan for choosing an AI model for your use case, with 10 test prompts, a scoring rubric and a blank results table.

Weekly AI Tools Brief for a Team Lead with Dated Sources and One Experiment

Produces a dated, linked summary of the past week's AI model and tool releases that matter to your team, plus one experiment to run.

Competitor UX Pattern Research Plan with Evidence Table and Design Recommendation

Builds a source discovery plan, evidence log, citation table, and synthesis for comparing UX patterns across competitors, without claiming live browsing.

Fact-Check a Viral Claim With Primary Sources and a Confidence Rating

Checks a claim you saw online against primary sources, traces where it came from, and returns a verdict with a confidence rating and the evidence on both sides.

Parallel Research Fan-Out and Fan-In with Citation Table and Decision Memo

Splits a research question across parallel research agents, defines source discovery and evidence review steps, merges findings into a citation table, and produces a decision memo without claiming live browsing.

Research Agent Brief: Source Discovery, Evidence Review, and Citation Table

Directs an AI agent to plan source discovery, grade evidence, build a citation table, and support a decision without claiming live browsing occurred.

Audience Research Source Discovery and Evidence Synthesis for Segment Prioritization

Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.

Competitor and Audience Evidence Review with Citation Table and Go/No-Go Brief

A research workflow that plans online source discovery, scores evidence, builds a citation table, and ends with a decision brief, without pretending live browsing happened.

Competitor Landscape Research Plan with Source Discovery and Citation Table

Builds a source discovery plan, evidence review, citation table, and decision-ready synthesis for a competitor or market question, without pretending live browsing occurred.