bip-lit-extract

name	bip-lit-extract
description	Extract paper references and concepts from a LaTeX repository for the bipartite knowledge graph.

Extract References from LaTeX Repository

Analyze a LaTeX repository to extract papers and concepts for the bipartite knowledge graph.

Usage

/bip-lit-extract <path-to-tex-repo>

What This Skill Does

1. Reads main.bib and main.tex from the specified repository
2. Extracts citation keys and their context from the manuscript
3. Identifies key concepts and potential relationships
4. Filters out software/tool citations (e.g., packages, libraries)
5. Returns a structured summary with:
   • Papers found (using BibTeX citation keys as bip IDs)
   • Suggested concepts to create
   • Potential edges to add

Workflow

Given a path like ../dasm-tex-1, perform this analysis:

Step 1: Read the BibTeX file

cat <repo>/main.bib

Extract citation keys (the part after @article{ or @inproceedings{, etc.).

Step 2: Read the manuscript

cat <repo>/main.tex

Look for:

• \cite{...} commands and their surrounding context
• Section structure to understand paper focus
• Key methodological terms

Step 3: Identify Concepts

Look for recurring themes that could become concept nodes:

• Methods mentioned repeatedly
• Domain-specific terms
• Mathematical frameworks
• Data types or experimental approaches

Step 4: Generate Output

Produce a structured summary:

{
  "papers": [
    {"id": "Smith2026-ab", "role": "foundational", "context": "Defines the X model"},
    {"id": "Jones2025-xy", "role": "applies", "context": "Uses X for Y analysis"}
  ],
  "suggested_concepts": [
    {"id": "x-model", "name": "X Model", "description": "Statistical framework for..."},
    {"id": "y-analysis", "name": "Y Analysis", "description": "Method for..."}
  ],
  "suggested_edges": [
    {"source": "Smith2026-ab", "target": "x-model", "type": "introduces", "summary": "Foundational paper"},
    {"source": "Jones2025-xy", "target": "x-model", "type": "applies", "summary": "Application to Y"}
  ]
}

Filtering Rules

Skip these citation types:

• Software packages (R packages, Python libraries)
• Datasets without methodology
• Generic references (textbooks, review articles) unless central to the paper
• Self-citations to prior versions of the same work

Prioritize these:

• Papers that introduce methods used in the manuscript
• Papers being compared against
• Foundational papers for the domain
• Papers being extended or built upon

Integration with bip

After running this skill, use the output to update the knowledge graph:

# Check which papers exist in bip
bip get Smith2026-ab

# Create suggested concepts
bip concept add x-model --name "X Model" --description "..."

# Add edges
bip edge add -s Smith2026-ab -t x-model -r introduces -m "Foundational paper"

Example Session

User: /bip-lit-extract ../dasm-tex-1

Claude: I'll analyze the LaTeX repository to extract references and concepts.

[Reads main.bib and main.tex]

Found 45 citations in main.bib. Here's my analysis:

**Key Papers** (12 identified as significant):
1. Halpern1998-yc - introduces mutation-selection model
2. Yaari2013-dg - introduces S5F targeting model
...

**Suggested Concepts** (4):
1. `mutation-selection-model` - Framework for codon substitution
2. `shm-targeting` - Somatic hypermutation targeting patterns
...

**Suggested Edges** (8):
- Halpern1998-yc --[introduces]--> mutation-selection-model
- Yaari2013-dg --[introduces]--> shm-targeting
...

Would you like me to:
1. Check which papers are already in your bip library?
2. Create these concepts and edges?