<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> PaperJury provides researchers with a structured, AI-driven pre-submission review for academic papers. It addresses the common issue of generic or unhelpful AI feedback by identifying critical argumentation gaps, experimental support weaknesses, and desk-rejection risks, enhancing paper quality and readiness for peer review.

How It Works

The core "review → adjudicate → revise → re-verify" engine mimics peer review, classifying AI feedback into "Safe Fix" (textual), "Author Handling" (experimental/evidence), and "Invalid" (misinterpretation). It combines AI agents for semantic analysis with deterministic scripts for verifiable checks, routing issues by disputability and applying risk-based guardrails.

Quick Start & Requirements

Installation is via the Claude Code plugin marketplace (/plugin marketplace add u7079256/paperjury, /plugin install paperjury@u7079256) or by cloning. Node.js is a prerequisite for deterministic checks. A LaTeX toolchain is optional but recommended for full compilation/layout verification; the system degrades gracefully if absent. A dogfood sample demonstrates a realistic run.

Highlighted Details

• Processes Word (.docx) files by converting to Markdown, preserving the original.
• Features three modes: direct-edit (minor changes), review (feedback), and auto (multi-round revisions, requires authorization).
• Employs a "courtroom" analogy for its engine, with bounded reviewers and issue adjudication.
• Includes deterministic checks for document decomposition, cross-references, and LaTeX compilation/layout.
• A peer-reviewed paper is available on arXiv: https://arxiv.org/abs/2606.16322.

Maintenance & Community

Recent activity includes v1.0.0 release (June 10, 2026) and Codex version push (June 5, 2026). A non-blocking soft update check for stable releases runs on startup. Extensive documentation is provided.

Licensing & Compatibility

The provided README content does not specify a software license, requiring clarification for commercial use or closed-source linking.

Limitations & Caveats

PaperJury is a self-check tool, not a replacement for author judgment or peer review. It cannot fabricate experiments or support unsupported claims. Issues requiring new experiments or private author knowledge are deferred. The system degrades if the LaTeX toolchain is unavailable, limiting verification.