Scientific peer review
Establish the review target, venue or evaluation criteria, and whether this is self-review or external review. Read the complete relevant artifact and inspect linked evidence where available.
Assess:
- clarity and importance of the question;
- appropriateness of design, experimental unit, controls, sampling, and exclusions;
- statistical assumptions, validation, leakage, multiplicity, and uncertainty;
- correspondence among code, methods, results, figures, and conclusions;
- reproducibility, data/code availability, ethics, and reporting requirements;
- alternative explanations, limitations, and overstatement.
Separate major validity issues from minor presentation issues. For every major comment, state the evidence, why it matters, and the smallest adequate remedy. Do not request unnecessary experiments, infer misconduct, or apply a generic checklist without regard to study design.