Claim Extractor

Workflow

Per draft:
- [ ] Step 1: Segment draft by heading / section
- [ ] Step 2: Within each section, split by sentence
- [ ] Step 3: Flag sentences containing technical claims:
    - Math symbols / formulas
    - Named systems, components, algorithms
    - Quantitative assertions
    - Universal quantifiers ("always", "never", "all models")
    - Named papers / results
- [ ] Step 4: Coalesce adjacent claim sentences that argue the same thing into one claim
- [ ] Step 5: Output numbered list: {id, excerpt (≤200 chars), location}

Non-claim content (skip)