docs: draft agent-oriented linting paper

[danielchen0]

Summary

Drafts an arXiv-style paper for laint around the idea of agent-oriented linting for generated JSX/TSX applications. The draft frames laint as a feedback-loop tool for catching framework-specific generated-app failures before build, preview, or runtime.

This is intentionally a draft PR: the paper has the system description, rule taxonomy, and evaluation plan, but still needs measured results before it should be treated as submission-ready.

Verification

• make in paper/ builds main.pdf cleanly
• Checked paper/main.log for undefined refs/citations and overfull/warning/error lines

Next

• Add real authors/affiliations
• Run the evaluation over generated app traces
• Replace the evaluation-plan section with measured results
• Add any venue-specific formatting if we target a workshop as well as arXiv