research-review

To get critical feedback on your research paper, provide your draft ideas, claims, and experimental results for external review. It identifies logical gaps, missing experiments, and narrative weaknesses, returning a high-signal critique to strengthen your work for acceptance.

A claims matrix is an actionable deliverable generated during research review that maps your arguments against evidence. It helps with peer review by highlighting where logical gaps or missing experiments exist, driving iterative refinement until claims and evidence converge.

To review research ideas for missing experiments, submit your topic scope, relevant papers, and experiment history. A multi-round external critique evaluates evidence against claims, producing a prioritized TODO list and experiment plan to address weaknesses before submission.

Yes, you can use multi-round evaluation for iterative refinement of ML experiments. By providing experiment history and results, the review process addresses weaknesses and follow-ups thread-by-thread until feedback converges on solid claims and experimental validation.

No, generating review reports requires access to a configured reviewer client. While you can provide context briefings and use thread-based dialogue continuity via a reviewer script, full multi-round evaluation and document generation depend on this client connection.