Local AI pre-screening for human triple-blind peer review in health sciences

[2608.14625] Local AI pre-screening for human triple-blind peer review in health sciences Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computers and Society arXiv:2608.14625 (cs) [Submitted on 18 Jul 2026] Title: Local AI pre-screening for human triple-blind peer review in health sciences Authors: Rodrigo Martins Boos View a PDF of the paper titled Local AI pre-screening for human triple-blind peer review in health sciences, by Rodrigo Martins Boos View PDF HTML (experimental) Abstract: Academic peer review is under mounting strain: NeurIPS 2025 received 21,575 submissions, ICLR 2025 received 11,603, and ICML 2025 received 12,107. This volume has outpaced the supply of qualified reviewers, and large language models (LLMs) are already filling the gap, largely undisclosed. An independent analysis of ICLR 2026 found roughly 21% of its 75,800 peer reviews were fully AI-generated, with over half showing some AI involvement (up from 15.8% in 2024). Documented risks include hallucinated citations in accepted papers and hidden prompt-injection instructions embedded in manuscripts to manipulate AI reviewers into favorable assessments. We propose a triple-blind, multi-LLM pre-screening framework for peer review, developed for a health sciences journal, that formalizes and discloses AI involvement while preserving human reviewers as the final decision-making authority. The framework routes a submission through five stages -- sanitization/anonymization, parallel AI pre-screening, an automated check gate, blinded human review, and editorial adjudication -- with return-to-author loops at the check and editor stages. Addressing the confidentiality concerns behind NIH/NSF bans on submitting unpublished proposals to third-party generative AI, all three AI reviewers run on locally-hosted, open-weight LLMs, keeping manuscript content within the journal infrastructure. The closest precedent, Shen et al., benchmarked five open-source LLMs on quartile classification of 200 manuscripts and found accuracy insufficient (35% exact-match) for autonomous use, supporting our decision to retain mandatory human adjudication. This transparent, human-supervised design offers a defensible alternative to today's opaque, unregulated AI use in peer review, potentially reducing the substantial delay of traditional review (avg. 13 weeks to first decision) without displacing human judgment. Comments: 16 pages, 1 figure Subjects: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI); Digital Libraries (cs.DL) ACM classes: H.3.7 Cite as: arXiv:2608.14625 [cs.CY] (or arXiv:2608.14625v1 [cs.CY] for this version) https://doi.org/10.48550/arXiv.2608.14625 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.5281/zenodo.21365017 Focus to learn more DOI(s) linking to related resources Submission history From: Rodrigo Boos [ view email ] [v1] Sat, 18 Jul 2026 00:06:33 UTC (201 KB) Full-text links: Access Paper: View a PDF of the paper titled Local AI pre-screening for human triple-blind peer review in health sciences, by Rodrigo Martins Boos View PDF HTML (experimental) TeX Source view license Current browse context: cs.CY < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.DL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• NURSE-AI: A nurse-by-design framework for multi-sensor, AI-enabled chronic wound assessment in community healthcare.#242050
• The economic imperative of artificial intelligence in maternal and neonatal health: a review of evaluation benefits, frameworks, challenges, future perspectives, and limitations.#125631
• The determinants of health assessment in the United States#175818
• Genetic Risk-Based Atrial Fibrillation Screening (GeneAF Study)#864699
• AI-DRIVEN RECRUITMENT: UNCOVERING AND MITIGATING LATENT BIAS IN RESUME SCREENING ALGORITHMS#186891