claude

aminer-exp-extraction

实验数据提取:论文 Markdown 经 GLM 句子过滤与结构化抽取(两个阶段均调用智谱 BigModel 公共 API,需 BIGMODEL_API_KEY),输出方法/数据集/指标/关键结果 JSON;PDF 请先用 aminer-pdf-ocr 转成 Markdown

67 on GitHubMITupdated 6 days ago
/

Plugin aminer-exp-extraction from marketplace aminer-open-skills in AMinerOrg/aminer-open-skill. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (1)

  • aminer-exp-extraction

    [Activation] Use when the user provides paper markdown file(s) and requests experiment data extraction (methods, datasets, metrics, results). [Scope] For each paper md: preprocess -> GLM sentence filter (glm-5.3-flash, SciBERT replacement) -> LLM extraction (glm-5.3-flash) -> one JSON per paper. Bot

View source on GitHub

More from AMinerOrg/aminer-open-skill

All 21 plugins →

个性化论文推荐,根据研究主题、学者画像或作者信息推荐相关论文,支持飞书卡片与 Markdown 两种输出格式

1 skill · 1 command

67

深度综述文献收集,宿主模型多轮驱动 AMiner 检索与引用滚雪球,收集数百篇候选论文,无需额外 LLM 配置

1 skill · 1 command

67

PDF OCR 与结构化实验提取:将论文 PDF 提交至 AMiner 开放平台 PDF OCR 异步解析,产出全文 Markdown,并由 Agent 按内置提示词提取实验方法/数据集/指标等结构化信息

1 skill · 1 command

67

Audit a paper for potentially missing direct experimental baselines using experiment and citation evidence

1 skill · 1 command

67

引用忠实性核查:读取论文 PDF,抽取每处正文引用及其声称,联网检索被引原文,判定引用是否忠于原文(支持/部分支持/曲解/查无此说/无法核实),无需 API Key

1 skill · 1 command

67

深度研究:宿主模型驱动固定研究循环,结合 AMiner 开放平台与宿主原生 web 工具,产出带引用的分层研究报告与可复用的 Evidence Ledger 证据台账,无需额外 LLM 配置

1 skill · 1 command

67

Maintain aminer-exp-extraction?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins21 plugins