PaperJury: Due-Process Review for Bounded LaTeX Revision
- URL: http://arxiv.org/abs/2606.16322v1
- Date: Mon, 15 Jun 2026 07:29:34 GMT
- Title: PaperJury: Due-Process Review for Bounded LaTeX Revision
- Abstract summary: PaperJury is a closed-loop review-verdict-revise-verify system built on a deterministic-semantic split.<n>PaperJury combines bounded holistic review, contestability-based routing, a due-process trial, and risk-proportional guard chains for anchor-bounded edits.
- Score: 10.41008524026468
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation [54.82704239643649]
We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans.<n>Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback.<n>We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness.
arXiv Detail & Related papers (2026-09-08T17:30:16Z) - Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems [0.0]
This paper contributes a formal mapping from hadith-science concepts to multi-agent pipelines.<n>It implements a relational schema implementing claim chains and a graded narrator registry.<n>The evaluation validates weakest-link quarantine and independent-chain corroboration.<n>It reports a partial failure of the grade-recovery loop, which missed the highest-fault narrator.
arXiv Detail & Related papers (2026-07-27T07:57:31Z) - Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization [1.1168121941015015]
Claim-Anchored Multi-document Summarization framework ( CAMS)<n>Claim-Anchored Multi-document Summarization framework ( CAMS)
arXiv Detail & Related papers (2026-06-22T22:39:08Z) - Cross-Source Reasoning-based Correction for Author Name Disambiguation [24.49534181014346]
Author name disambiguation is a critical challenge in academic search systems.<n>We propose CrossND, a full-stack framework that integrates data refinement, cross-source reasoning, and test-time scaling.<n>Experiments on real-world datasets indicate that CrossND consistently outperforms 17 baselines.
arXiv Detail & Related papers (2026-06-07T13:08:15Z) - Shattering the Echo Chamber: Hidden Safeguards in Manuscripts Against the AI Takeover of Peer Review [41.467123148467415]
End-to-End Review Outsourcing is an emerging threat.<n>We propose IntraGuard, a venue-agnostic defense framework.<n>We show that IntraGuard achieves a defense success rate of up to 84%.
arXiv Detail & Related papers (2026-05-06T13:23:40Z) - When AI reviews science: Can we trust the referee? [73.47745294608072]
We map attacks across the review lifecycle -- training and data retrieval, desk review, deep review, rebuttal, and system-level.<n>We use two advanced LLM-based referees to isolate the causal effects of prestige framing, assertion strength, rebuttal sycophancy, and contextual poisoning on review scores.
arXiv Detail & Related papers (2026-04-26T08:03:32Z) - What Makes a Good AI Review? Concern-Level Diagnostics for AI Peer Review [6.59569431190247]
We propose a diagnostic framework that evaluates AI reviews at the concern level rather than only at the verdict level.<n>We derive an evaluation ladder that moves from binary accuracy to concern detection, verdict-stratified behavior, decision-aware calibration, and rebuttal-aware decomposition.
arXiv Detail & Related papers (2026-04-21T21:16:59Z) - PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review [54.141490756509306]
We introduce PaperAudit-Bench, which consists of two components: PaperAudit-Dataset, an error dataset, and PaperAudit-Review, an automated review framework.<n>Experiments on PaperAudit-Bench reveal large variability in error detectability across models and detection depths.<n>We show that the dataset supports training lightweight LLM detectors via SFT and RL, enabling effective error detection at reduced computational cost.
arXiv Detail & Related papers (2026-01-07T04:26:12Z) - BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? [21.78901120638025]
We investigate whether fabrication-oriented paper generation agents can deceive multi-model LLM review systems.<n>Our generator employs presentation-manipulation strategies requiring no real experiments.<n>Despite provably sound aggregation mathematics, integrity checking systematically fails.
arXiv Detail & Related papers (2025-10-20T18:37:11Z) - End-to-End Page-Level Assessment of Handwritten Text Recognition [69.55992406968495]
HTR systems increasingly face the end-to-end page-level transcription of a document.
Standard metrics do not take into account the inconsistencies that might appear.
We propose a two-fold evaluation, where the transcription accuracy and the RO goodness are considered separately.
arXiv Detail & Related papers (2023-01-14T15:43:07Z) - Mitigating Manipulation in Peer Review via Randomized Reviewer
Assignments [96.114824979298]
Three important challenges in conference peer review are maliciously attempting to get assigned to certain papers and "torpedo reviewing"
We present a framework that brings all these challenges under a common umbrella and present a (randomized) algorithm for reviewer assignment.
Our algorithms can limit the chance that any malicious reviewer gets assigned to their desired paper to 50% while producing assignments with over 90% of the total optimal similarity.
arXiv Detail & Related papers (2020-06-29T23:55:53Z) - Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised
Deep Asymmetric Metric Learning [62.34197797857823]
A central problem in automatic reconstruction of shredded documents is the pairwise compatibility evaluation of the shreds.
This work proposes a scalable deep learning approach for measuring pairwise compatibility in which the number of inferences scales linearly.
Our method has accuracy comparable to the state-of-the-art with a speed-up of about 22 times for a test instance with 505 shreds.
arXiv Detail & Related papers (2020-03-23T03:22:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.