Cross-Reference Claim

Source hierarchy (enforced)

1. Primary: original arXiv paper, official docs (PyTorch, CUDA, Linux), RFC, ACM/IEEE proceedings, canonical textbook (Deep Learning Goodfellow et al., DDIA Kleppmann, Jurafsky & Martin).
2. Secondary: author's own blog/slides when they are the primary authority; well-maintained official implementation source.
3. Tertiary: Wikipedia (orientation only, never as the cite).
4. Not a source: random blog posts, Medium, X threads, unreviewed tutorials, other LLM outputs.

Workflow

Per claim:
- [ ] Step 1: WebSearch with claim + likely source terms
- [ ] Step 2: WebFetch top candidate; extract specific result/passage
- [ ] Step 3: If paywalled, fall back one tier; note fallback explicitly
- [ ] Step 4: If nothing authoritative within 10 min on one claim, mark could-not-verify
- [ ] Step 5: Return {url, title, passage_or_result, tier}