# LIMITATIONS (verified, 2026-11-03)

1. No human evaluation. The mandate's H1 (blind human-rated) could not be tested; all quality outcomes are LLM-judge ratings (claude-sonnet-5-5) with a measured self-consistency check; judge biases (verbosity, style preference, same-vendor affinity) are not eliminated.
2. Single journal, four volumes. Profiles describe JoF 2017–2020 practice (263 articles, 4 presidential addresses, 8 corrigenda/replications, 1 retracted article); they are not finance-wide norms and not editorial requirements.
3. Annotation is model-based. The rhetorical annotations come from claude-opus-5-5 with schema validation and deterministic cross-checks (roadmap regex, contribution regex, magnitude regex, section-role rules). Model–rule agreement is reported; it is not human inter-rater reliability. ~10% of first-pass annotations failed strict schema validation and were re-run (see PROGRESS.md).
4. Parser is heuristic. Layout heuristics tuned to the JoF LaTeX template; cross-parser agreement on a stratified sample is reported in data/derived/parser_qa.md (sections exact 85%, tables within ±1 96%, figures exact 92%, references within 10% 92%; numbered-equation counts are approximate). Corrigenda and one-page notes parse with low confidence and are excluded from rhetoric profiles by genre.
5. Pretraining contamination. The generator and judge may have seen the held-out articles; mitigations (withheld introductions, overlap screening, citation verification against the reference list) reduce but do not remove this.
6. Small experimental sample. Two held-out finance documents × 8 tasks (+ one out-of-domain manuscript), one to two repetitions: a pilot of the protocol, powered to detect only large effects; results are reported with CIs and Holm correction and must not be over-read.
7. Conditions differ in token budget. E makes two generation calls (draft + referee) and therefore uses more tokens than A–D; cost and latency are reported as outcomes, not controlled.
8. Engine scope. Numeric-preservation checks compare number sets, not meanings; "unsupported claim" detection is a regex heuristic; citation verification checks keys and DOIs, not whether the cited work supports the claim.
9. Platform: tested on one Mac; the Claude Code integration targets version 2.1.317's command/agent/skill formats.