# PaperJury: Due-Process Review for Bounded LaTeX Revision

arXiv: https://arxiv.org/abs/2606.16322 · HTML: https://mlsanity.com/paper/2606.16322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [Automated Focused Feedback Generation for Scientific Writing Assistance](https://mlsanity.com/paper/2405.20477/) (2024)
- [TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review](https://mlsanity.com/paper/2506.07642/) (2025)
- [Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction](https://mlsanity.com/paper/2509.18658/) (2025)
- [Are We on the Right Way to Assessing LLM-as-a-Judge?](https://mlsanity.com/paper/2512.16041/) (2025)
- [Multi-Agent Debate for LLM Judges with Adaptive Stability Detection](https://mlsanity.com/paper/2510.12697/) (2025)
- [PresentAgent: Multimodal Agent for Presentation Video Generation](https://mlsanity.com/paper/2507.04036/) (2025)
- [TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories](https://mlsanity.com/paper/2604.07223/) (2026)
- [BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2602.09383/) (2026)
- [Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines](https://mlsanity.com/paper/2604.23178/) (2026)
- [XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration](https://mlsanity.com/paper/2505.11336/) (2025)
- [PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing](https://mlsanity.com/paper/2512.02589/) (2025)
- [Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance](https://mlsanity.com/paper/2603.27360/) (2026)
- [Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification](https://mlsanity.com/paper/2603.28488/) (2026)
- [Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering](https://mlsanity.com/paper/2604.16790/) (2026)
- [Bias and Uncertainty in LLM-as-a-Judge Estimation](https://mlsanity.com/paper/2605.06939/) (2026)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2510.18196/) (2025)
- [Metamodel-Guided Model Generation with Layered Constraints](https://mlsanity.com/paper/2510.25890/) (2025)
- [I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications](https://mlsanity.com/paper/2606.00750/) (2026)

## Built on by (most cited first, 1 of 1)

- [PatchWrite: One Line, Not One Section -- Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts](https://mlsanity.com/paper/2608.23001/) (2026)

## Abstract (arXiv)

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.