PaperJury: Due-Process Review for Bounded LaTeX Revision
2026-06-15 • Computation and Language
Computation and Language
AI summaryⓘ
The authors present PaperJury, a system designed to improve the final review and revision process of computer science papers written in LaTeX before submission. Unlike typical writing helpers, PaperJury uses a mix of fixed rules (deterministic orchestration) and smart AI agents for controlled reviewing and editing. This approach ensures clear decisions on problems found, tracks changes carefully, and safely applies fixes without letting the AI make unchecked changes. Their tests on papers in vision, NLP, and machine learning show better handling of issues compared to other methods. The authors argue that reliable review outcomes depend more on fixed procedures than on open-ended AI choices.
LaTeXadversarial reviewdeterministic orchestrationsemantic agentsholistic reviewroutingclaim spineedit safetynatural language processingmachine learning
Authors
Yiran Wang, Ruixuan An, Biao Wu, Wenhao Wang
Abstract
Pre-submission hardening of human-authored LaTeX computer science papers differs from drafting assistance because it requires adversarial whole-paper review, explicit no-fix outcomes, and bounded artifact-safe revision. Existing writing assistants, critique generators, and judge-centered loops lack durable issue identity across rounds, deterministic routing from critique to adjudication, and manuscript control that can reject invalid concerns or defer author-dependent ones. We present PaperJury, a closed-loop review-verdict-revise-verify system built on a deterministic-versus-semantic split: deterministic orchestration manages decomposition, a frozen claim spine, a durable ledger, routing, stopping, and exact-once patch application, while semantic agents are limited to bounded review, judgment, and repair. PaperJury combines bounded holistic review, contestability-based routing, a due-process trial, and risk-proportional guard chains for anchor-bounded edits, yielding terminal outcomes of invalid-drop, valid-fixable, and author-required. In a two-arm expert-review evaluation on held-out Vision, natural language processing, and machine learning papers against four baselines, we assess issue quality, verdict and routing quality, edit safety, convergence behavior, and cost, supporting the thesis that load-bearing safety and completion logic should reside in deterministic orchestration rather than model discretion. PaperJury is available at https://github.com/u7079256/paperjury.