PaperJury: Due-Process Review for Bounded LaTeX Revision

2026-06-15

AI Summary

Existing writing assistance tools struggle to provide holistic, adversarial review of LaTeX manuscripts and lack mechanisms to ensure consistency and safety across multiple revision rounds. This work proposes a safety-oriented revision paradigm governed by deterministic orchestration, establishing a closed-loop system that integrates review, adjudication, revision, and verification. By decoupling semantic tasks from deterministic workflows, the approach introduces persistent issue identifiers, claim-trunk freezing, anchored boundary editing, and dispute routing strategies to enable traceable, structure-preserving revisions with controllable risk exposure. The system supports three terminal adjudication outcomes: discard as invalid, revise as valid, or escalate for author intervention. Expert evaluations on papers from computer vision, natural language processing, and machine learning demonstrate that the proposed method significantly outperforms four baselines in terms of issue quality, adjudication accuracy, editing safety, convergence, and cost efficiency.

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.

Problem

• LaTeX revision
• due-process review
• bounded editing
• adversarial review
• manuscript hardening

Innovation

• deterministic orchestration
• bounded revision
• due-process review
• anchor-bounded edits
• closed-loop verification