PaperJury: Due-Process Review for Bounded LaTeX Revision
For computer science researchers seeking robust pre-submission review, PaperJury provides a principled framework that ensures due process and bounded revisions, addressing the lack of durable issue tracking and safe automated editing in existing tools.
PaperJury introduces a closed-loop review-verdict-revise-verify system for pre-submission LaTeX paper hardening, using deterministic orchestration to manage review, routing, and edits while limiting semantic agents to bounded tasks. In expert evaluation on Vision, NLP, and ML papers, it outperformed four baselines in issue quality, verdict accuracy, edit safety, and convergence, supporting that safety logic should be deterministic.
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.