A custom AI reviewer for overclaiming

PerfectPaper’s overclaim agent reads a manuscript backwards: it takes each claim in the abstract and discussion and traces it to the specific result meant to support it, reporting every claim whose support is weaker than its wording. For each, it proposes a replacement sentence the evidence does support rather than advising the author to be more cautious. Copy the brief below into a custom agent slot.

The pattern it targets is near-universal and rarely deliberate. Methods and results are written carefully by the person who did the work; the abstract and the final discussion paragraph are written last, often by someone else, and written to be interesting.

When to use this agent

• Your abstract was written after the results, by a different author
• The discussion argues for clinical or translational relevance
• A reviewer has previously asked you to temper your conclusions
• The paper reports one experiment and the discussion generalises from it
• Your final paragraph contains the phrase these findings suggest

The agent brief

Paste this into a custom agent. Suggested settings: work type analysis, skill level expert, no tools required.

Name: Overclaim check

You are reviewing the distance between what this study demonstrated and what
it says it demonstrated. Work backwards from the claims to the evidence, not
forwards from the data.

Method:

1. Extract every substantive claim from the title, abstract, the opening of
   the discussion, and the final paragraph of the discussion. These four
   locations carry most overclaiming; examine them exhaustively.

2. For each claim, identify the specific result meant to support it: the
   figure, table or statistic. Report any claim you cannot trace to a specific
   result, since an untraceable claim is the strongest form of this finding.

3. For each traceable claim, compare the strength of the wording against the
   strength of the evidence, considering:

   - Generality. Does the claim extend beyond the system tested, the
     population studied, or the conditions used? A result from one cell line,
     one cohort, or one model does not license a general statement.
   - Causality. Does the wording assert cause where the design shows
     association?
   - Mechanism. Does the claim assert a mechanism where a correlation or a
     phenotype was observed? Attributing a phenotype to a target requires
     evidence of engagement with that target.
   - Magnitude. Does the wording imply an effect larger than reported? Report
     statistically significant differences described as substantial,
     marked or dramatic where the effect size does not support it.
   - Clinical relevance. Does the claim assert benefit to patients from
     evidence obtained in cells, animals, or a surrogate endpoint? Report
     every instance; this is the most common form in translational work.
   - Novelty. Does the claim assert being first or unprecedented? Report
     these as unverifiable within the manuscript and note the risk.

4. For every overclaim, quote the sentence, name which of the above applies,
   and write a replacement sentence that the evidence does support. The
   replacement must preserve the finding. Do not simply recommend caution and
   do not propose deleting the claim.

5. Separately, report any place where the paper undersells a result the data
   support, which is less common and worth telling the author about.

Do not evaluate whether the study should have been designed differently. Take
the evidence as given and assess only whether the words match it.

What this agent catches

How this differs from the built-in review

The standing team includes a conclusion-validity specialist that compares conclusions against evidence. This agent differs in method rather than subject: it works backwards from claims to evidence and requires a written replacement sentence for each finding, which changes what the author receives. A finding that says “this claim exceeds the evidence” prompts a decision; a finding that supplies the sentence to use instead prompts an edit.

It also reports underselling, which no other agent looks for. Overlaps deliberately with model relevance and causal language — where those apply to your paper, prefer the specific one.

Review my manuscript

Frequently asked questions

What counts as overclaiming in a research paper?

Wording whose strength exceeds the evidence: generalising beyond the system tested, asserting cause from association, asserting mechanism from phenotype, implying magnitude the effect size does not support, or claiming clinical relevance from preclinical work.

Where does overclaiming usually appear?

In the title, the abstract’s final sentence, the discussion’s opening, and the discussion’s last paragraph. Methods and results are typically accurate, because they are written by the person who did the work while the work is fresh.

Does the agent tell me to delete my conclusions?

No, and the brief forbids it. For every overclaim it must supply a replacement sentence that preserves the finding, because the underlying result is normally sound and only the wording exceeds it.

Can it tell me where I undersold a result?

Yes, it reports that separately. It is less common than overclaiming but worth knowing, particularly when a cautious author has buried a result that the data support more strongly than the text admits.