PaperJury: Due-Process Review for Bounded LaTeX Revision
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
23 of 29 references.
References · 23
- 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
- 2024Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judgecited by 269
- 2025DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Processcited by 100
- 2025Evaluating Scoring Bias in LLM-as-a-Judgecited by 43
- 2024Automated Focused Feedback Generation for Scientific Writing Assistancecited by 33
- 2025TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Reviewcited by 31
- 2025Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Predictioncited by 27
- 2025Are We on the Right Way to Assessing LLM-as-a-Judge?cited by 24
- 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detectioncited by 23
- 2025PresentAgent: Multimodal Agent for Presentation Video Generationcited by 21
- 2026TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectoriescited by 16
- 2026BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluationcited by 14
11 more
- 2026Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelinescited by 8
- 2025XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaborationcited by 7
- 2025PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editingcited by 6
- 2026Defend: Automated Rebuttals for Peer Review with Minimal Author Guidancecited by 4
- 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verificationcited by 4
- 2026Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineeringcited by 4
- 2026Bias and Uncertainty in LLM-as-a-Judge Estimationcited by 4
- 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
- 2025Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judgecited by 3
- 2025Metamodel-Guided Model Generation with Layered Constraintscited by 3
- 2026I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applicationscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.