Loading page…
Explore ArkGraph and select the steps to run.
PaperDoctor is an agent framework for diagnosing draft scientific papers rather than issuing acceptance verdicts. It parses manuscripts and code, performs low-cost writing, visual, citation, and claim screening, routes extracted claims to code, theory, literature, and experiment-design verifiers, and selectively reruns experiments. Each finding links an observation to source evidence and a proposed revision. The paper evaluates author responses on 30 in-progress papers and compares PaperDoctor with referees and an agentic reviewer on 40 papers across four domains. It also analyzes experiment reproduction, showing both frequent pre-execution blockers and substantial post-execution mismatches.
The work suggests that automated review can be made more useful to authors by pointing to exact evidence and proposing a concrete fix, while also checking code and rerunning selected results that reading-only review misses. Its evidence is not uniformly positive: authors reject many surface and figure critiques, almost half of reproduction plans never run, many executed plans do not pass, and the strongest checks depend on runnable code. The system is presented as support for checkable details, not a replacement for human judgment about novelty, importance, or scientific taste.
The paper’s claims are available in Research claims.
Past research reports
Saved reports remain available. New report generation is paused.