aerj-tables-figures — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited aerj-tables-figures (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
In AERJ, a reader should grasp each exhibit without hunting through the text, and every exhibit must follow APA 7th-edition table/figure conventions. Because review is masked, exhibits must carry no identifying clues (institution names, data-source giveaways in titles).
sample/N, the units, and significance/probability conventions. A reader should not need the text.
figure number + title; a general note, then specific notes, then probability notes.
levels and random effects; mark the estimand, not just stars.
interactions, distributions, RD/event-study, joint displays for mixed methods). Otherwise use a table.
output for line art.
quotation) are legitimate exhibits — anonymize participants and sites.
materials (see aerj-transparency-and-data-policy).
Generate exhibits from the fitted result, not by retyping numbers (the usual source of body-vs-supplement drift). Full map: execution-with-mcp. AERJ is empirical education research — field experiments and observational school data; multilevel inference and many-outcome corrections are central.
etable (multi-model columns) or did_summary_to_latex straight from theresult_id.
plot_from_result / enhanced_event_study_plot / event_study_table —axis units and the SE/clustering note baked in.
interpretable units.
See a full fitted-result → exhibit chain in the JF execution walkthrough.
Reviewers across AERJ's policy/institutional, teaching/learning, development, and cross-cutting lenses read exhibits before they read prose, so an unreadable exhibit damages the paper before the argument is even heard. Use this as a pre-submission exhibit triage.
| Exhibit type | What an AERJ referee expects to see | Desk-screen / first-round red flag |
|---|---|---|
| Multilevel results table | Level-1 and level-2 coefficients separated, random-effect variances, ICC, N at each level | One undifferentiated column that hides the nesting |
| Growth-model table | Intercept/slope means, variance components, time coding stated | Trajectories implied but no variance components reported |
| Quasi-experimental figure | Event-study or RD plot with bandwidth, pre-trend, confidence band | A bare bar chart of means with no uncertainty |
| Qualitative evidence table | Theme → operational definition → exemplar excerpt → source (anonymized) | A wall of quotations with no analytic column |
| Mixed-methods joint display | Quant result and qual finding side by side with a meta-inference column | Two stacked exhibits that never meet |
Take an AERJ study of a middle-school reading-comprehension intervention in 40 schools. The core table reports a treatment coefficient of 0.18 SD (95% CI [0.04, 0.32]), a school-level ICC of 0.14, and N = 3,200 students in 40 schools (all numbers illustrative). A strong AERJ exhibit puts the estimate, the interval, the ICC, and both N levels in one self-contained note; a weak one prints "b = 0.18, p < .05" and forces the reader into the methods section to learn the sample is clustered. The companion joint display pairs that 0.18 SD estimate with the qualitative finding that teachers in higher-gain schools re-allocated time to discussion — the meta-inference column is what earns the figure its place.
label random effects; report the ICC explicitly.
distinguishable markers/linetypes; SAGE print remains a constraint.
review requires anonymized exhibits, not just an anonymized text body.
【Exhibit】table / figure — one-line purpose
【Self-contained?】title + notes define N, units, abbreviations, significance [Y/N]
【APA 7th format】[Y/N]
【Uncertainty shown】SE/CI + estimand labeled [Y/N]
【Accessible】colorblind-safe + grayscale-legible [Y/N]
【Masked】no identifying clues [Y/N]
【Next】aerj-writing-style../../resources/external_tools.md — plotting/exhibit tooling and APA table helpers../../resources/official-source-map.md — APA style and masked-review requirements~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.