社区开发者基于 MiniCPM 推出可溯源文档校验智能体 TraceCell

OpenBMB· @OpenBMB · X·2026-11-11 21:30· 28 分钟前AI 评分51

AI 导读

OpenBMB 介绍社区开发者 @mucerx 基于 MiniCPM 构建的本地优先文档解析与校验智能体 TraceCell。三个模型协作：MiniCPM-OCR 1.0 解析文档，MiniCPM-OCR Jev 为识别候选打分，MiniCPM-V 4.7 复核模糊区域；每个字段回链源图坐标、置信度和复审状态，不确定结果触发重新解析、模型复核或人工介入，还可校验算术并对账。

正文 · 原文

📄 Can your document agent show why a result should be trusted and flag what needs another look?

Community developer @mucerx built TraceCell, a local-first document parsing and verification agent powered by MiniCPM. 🔍

Three models work together:
📖 MiniCPM-OCR 1.0 parses document content.
⚖️ MiniCPM-OCR Jev scores recognition candidates.
🧠 MiniCPM-V 4.7 reviews ambiguous regions, with its answers scored again before acceptance.

📍 Every field links back to source-image coordinates, confidence, and review status in an evidence ledger.

🔄 Uncertain results trigger targeted re-parsing, model review, or human escalation. Documents are routed for automatic acceptance, spot checks, or full review.

🧮 TraceCell also checks arithmetic and reconciles documents—catching mismatches even when the text itself was recognized correctly.

🧪 The author’s current demo covers 5 synthetic documents, 83 regions, and 52 business fields. Calibration on 78 labelled samples reports 80.77% automatic acceptance with no incorrect acceptances. These are sample-set results, not independently verified production guarantees.

With MCP and Skill support, it’s a practical community example of turning visual understanding into traceable decisions. 💙

🛠️ Explore TraceCell:
github.com/logicore-code/Trac…

🚀 Build with MiniCPM:
GitHub — MiniCPM-OCR:
github.com/OpenBMB/MiniCPM-OCR
GitHub — MiniCPM-V:
github.com/OpenBMB/MiniCPM-V
🤗 Hugging Face — MiniCPM-OCR 1.0:
huggingface.co/openbmb/MiniCP…

#MiniCPM #OpenBMB #DocumentAI #OpenSource

来源：OpenBMB · x.com