Overview
Open AI Xiv (OAIXiv) is an AI-driven academic preprint platform. After researchers upload a paper, the system automatically calls multiple large AI models (currently Mimo and Deepseek) for independent review, aggregates via voting, and within 3-5 minutes produces a structured quality-assessment report across six dimensions. In one line: upload paper → multi-model AI consult → see scores and concrete improvement suggestions on novelty, methodology, reproducibility, writing quality, literature coverage, and research importance. Core features 1. Multi-model AI review (core): not a single AI score. Three or more independent models each review the same dimension, take the median, and mark confidence. Larger model disagreement means lower confidence—you know at a glance whether the review is reliable. 2. Six-dimension structured report: not a vague blurb. Novelty, methodological rigor, reproducibility, writing quality, literature coverage, research importance—each scored independently (1-10) with concrete comments, strengths, gaps, and revision suggestions (high/medium/low priority). 3. Version evolution tracking: revise a version, re-review once. 4. Native multilingual review: AI can review Chinese papers directly—no English translation first. Bilingual Chinese–English UI and cross-language paper discovery. Use cases — Scene one: pre-submission "pre-checkup" when a first draft is done but quality is uncertain.
Connected profiles
More General-purpose agents products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
Open AI Xiv（OAIXiv）是一个AI驱动的学术论文预印本平台。研究者上传论文后，系统自动调用多个AI大模型（目前采用 Mimo和Deepseek）进行独立评阅，通过投票机制聚合，在3-5分钟内生成一份包含六个维度的结构化质量评估报告。一句话：上传论文 → AI多模型会诊 → 看到你的论文在创新性、方法论、可复现性、写作质量、文献覆盖度、研究重要性六个维度上的分数和具体改进建议。核心功能1. 多模型AI评阅（核心）不是单一AI打分。三个以上的独立AI模型各自独立评阅同一维度，取中间值聚合，标注射信度。模型间分歧越大，置信度越低——你一眼就知道这份评阅是否靠谱。2. 六维度结构化报告不是一段笼统的评语。创新性、方法论严谨性、可复现性、写作质量、文献覆盖度、研究重要性——每个维度独立打分（1-10分），附带具体评语、优点、不足和修改建议（标注高/中/低优先级）。3. 版本演化追踪论文改一版，重新评一次。4. 多语言原生评阅AI可以直接评阅中文论文，不需要先翻译成英文。中英文双语界面，跨语言论文发现。使用场景场景一：投稿前的"预体检"完成论文初稿，但不确定质量如何。