PeeriScope多维度评估学术审稿质量，助力提升评审透明度与效率。
PeeriScope: A Multi-Faceted Framework for Evaluating Peer Review Quality
- 融合结构化特征与大模型评分，多维度量化审稿质量。
- 支持自评、编辑筛选与大规模审计，可实时部署。
- 开源可扩展，适合研究者与期刊编辑使用。
学术会议中审稿规模与差异性日益增长，亟需系统化、可解释且可扩展的工具来评估审稿质量。我们提出PeeriScope，一个模块化平台，整合结构化特征、基于评分表的大语言模型评估以及监督预测，从多个维度评估审稿质量。平台设计开放，提供公开界面和文档化API，支持实际部署与研究扩展。演示展示了其在审稿人自评、编辑初筛和大规模审计中的应用，推动科学审稿质量评估方法的持续发展。PeeriScope可通过https://app.reviewer.ly/app/peeriscope在线体验，或通过GitHub（https://github.com/Reviewerly-Inc/Peeriscope）获取API服务。
原文摘要 · Abstract (English)
The increasing scale and variability of peer review in scholarly venues has created an urgent need for systematic, interpretable, and extensible tools to assess review quality. We present PeeriScope, a modular platform that integrates structured features, rubric-guided large language model assessments, and supervised prediction to evaluate peer review quality along multiple dimensions. Designed for openness and integration, PeeriScope provides both a public interface and a documented API, supporting practical deployment and research extensibility. The demonstration illustrates its use for reviewer self-assessment, editorial triage, and large-scale auditing, and it enables the continued development of quality evaluation methods within scientific peer review. PeeriScope is available both as a live demo at https://app.reviewer.ly/app/peeriscope and via API services at https://github.com/Reviewerly-Inc/Peeriscope.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。