AISTATS Supplementary

SkillDev tools

Use when preparing AISTATS supplementary material, appendices, proof details, code/data archives, simulation scripts, additional tables, and anonymized artifacts under deadline, size, anonymity, and reviewer-discretion constraints, including how to split a theory-plus-experiments paper between body and supplement.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the AISTATS Supplementary skill

What this skill tells your AI

The instructions your AI receives, as published by brycewang-stanford/awesome-journal-skills in AISTATS-Skills/skills/aistats-supplementary/SKILL.md and read by ahel’s review.

Use this when assembling AISTATS supplementary material. The supplement can support the paper, but the main submission must remain understandable without it.

Supplement structure

  • Put theorem proofs, derivations, extra ablations, simulation details, dataset documentation, and robustness tables in a clean appendix or supplementary manuscript.
  • Put executable assets in a separate archive when current OpenReview forms allow it.
  • Respect the current supplementary deadline. AISTATS 2026 placed supplementary-material submission after the paper deadline but before review.
  • Keep all supplementary files double-blind: no authors, institutions, acknowledgements, private paths, repository owners, grants, or identifying metadata.
  • Do not use the supplement to hide essential motivation, core method description, main theorem statements, or primary empirical results.
  • Verify archives open on a clean machine and contain no credentials, cache directories, large irrelevant files, or hidden OS metadata.

Appendix architecture for proofs

  • Order appendix sections to mirror main-text theorem order; statistician reviewers navigate by theorem number, not by page.
  • Restate each theorem before its proof so the appendix reads standalone without flipping back to the two-column body.
  • Standard partition: notation and assumptions, main proofs, auxiliary lemmas, additional simulations, then real-data details.
  • Keep one proof-sketch paragraph per major theorem in the body itself; an AISTATS submission whose entire argument lives in the supplement reads as unreviewable within the page limit.
  • Cross-reference every appendix table and lemma from the body at least once; orphaned supplement material is invisible to reviewers and wasted under reviewer discretion.
  • If the cycle allows appendices inside the main PDF after the references, confirm against the current instructions whether that or a separate file upload is expected.

What gets opened first

Supplement itemInspection likelihoodPractical implication
Proof of the headline theoremHighPolish it to main-text standard
Extra ablation and robustness tablesMediumReference each one from the body
Code archiveVariable, reviewer discretionThe README must orient a reader in one minute
Raw experiment logsLowInclude for completeness, never rely on them

Vignette: splitting an optimization paper

A submission proving a convergence guarantee for a stochastic mirror-descent variant, plus benchmark plots: the body keeps the theorem, the key lemma, the proof roadmap, and two decision-critical figures; the appendix holds full proofs and step-size sensitivity grids; the archive carries the seeded experiment runner. Nothing decision-critical lives only in the archive, because archive inspection at AISTATS is discretionary.

Output format

[Supplement status] Ready / Needs fixes / Not ready
[Files] <appendix/proofs/code/data/logs>
[Deadline] <current supplement deadline and source>
[Anonymity checks] <passed/issues>
[Main-paper dependency] <what breaks if supplement is ignored>

Signals

GitHub stars
1k
Forks
146
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
aistats-supplementary
Source
github.com/brycewang-stanford/awesome-journal-skills