triage-paper

Triage Paper

Add a new academic paper to the research repo as a structured reference summary.

When to Use

• User provides an arxiv ID (e.g. 2310.08560), arxiv URL, or paper PDF path
• User says "triage this paper", "add this paper", or "analyse this paper"
• Evaluating whether a paper belongs in the repo

When Not to Use

• The paper has already been triaged (check REVIEWED.md first)
• The paper is clearly out of scope (not related to the research domain)
• User wants a full deep-dive analysis — use triage-paper first, then promote to ANALYSIS-*.md

Recommended MCP Servers

When available, prefer these MCPs over WebFetch for paper discovery and metadata resolution — they return structured data and avoid HTML scraping.

{
  "mcpServers": {
    "semantic-scholar": {
      "type": "stdio",
      "command": "uvx",
      "args": ["semantic-scholar-fastmcp"]
    },
    "google-scholar": {
      "type": "stdio",
      "command": "uvx",
      "args": ["google_scholar_mcp_server"]
    }
  }
}

Use semantic-scholar as the primary source (open, structured, covers most CS/ML papers). Fall back to google-scholar for papers not indexed there. Fall back to WebFetch (arxiv abstract page) only when neither MCP is configured or returns results.

Mindset

Triage is a quality gate, not a data-entry task. The goal is a scannable, honest record.

1. Evidence first: quote what the paper reports; never infer or embellish claims.
2. Triage-then-promote: every paper enters via REVIEWED.md; promotion to ANALYSIS-*.md requires a deliberate user decision — never automatic.
3. Scope over completeness: a well-reasoned rejection is as valuable as a full summary. If the paper is tangentially related, triage it and flag it; don't silently skip it.

Workflow

1. Resolve the source

• If given an arxiv ID or URL: use the semantic-scholar MCP to resolve metadata (title, authors, date, abstract, DOI). If not configured, fall back to WebFetch on the arxiv abstract page.
• If given a DOI: prefer semantic-scholar or google-scholar MCP over a raw HTTP fetch.
• If given a PDF path, read it to extract the same fields.
• Derive a stable slug: <firstauthor-surname>-<2-3-word-topic> (e.g. jiang-llmlingua, press-longchat).