WILLOSCAR

Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.

Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid…

Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus…

Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to…

Use when a tutorial module plan exists but each module still needs a verifiable teaching loop.

Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation…

Global consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.

Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).

Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.

Scaffold a LaTeX project (`latex/main.tex`, optional bibliography wiring, structure) from an existing Markdown draft.

Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \\\"Two limitations…\\\")…