AAAI Submission
Use this for an AAAI main technical track submission audit. Reopen the current conference page,
Author Kit, CFP, submission instructions, review process page, supplementary-material page, and
author policies before giving deadline-ready advice.
Submission audit
- Confirm the target track: Main Track, AI for Social Impact, AI Alignment, or another AAAI program.
Track-specific rules can differ.
- Verify OpenReview account/profile readiness, conflicts, author list, subject areas, and submission
metadata before the abstract and paper deadlines.
- Check the current AAAI author kit. AAAI-26 submissions used AAAI two-column camera-ready style,
US Letter PDF, and 7 pages of technical content plus pages solely for references and the
reproducibility checklist.
- Confirm double-blind compliance in the PDF, file names, references to prior work, supplement,
code/data, and metadata. Omit acknowledgments in the review version.
- Include the reproducibility checklist after references when current instructions require it.
- Enforce the author submission limit and author-change rules. AAAI-26 limited each author to 10
combined technical-track submissions and did not allow authors to be added after submission.
- Check multiple-submission compliance. An AAAI submission under review cannot simultaneously be
under review at another archival venue.
- Apply the current AAAI AI-use policy: editing/polishing author-written text may be allowed, but
LLM-generated manuscript text, AI authorship, and AI-generated citations are policy risks.
Blocking risks
- Over-limit technical content or malformed PDF.
- Missing reproducibility checklist.
- Identity leakage in paper, supplement, links, code, data, or prior-work citations.
- Author added after the allowed window.
- Concurrent archival submission.
- Web pointers to mutable supplementary material.
- Policy-violating LLM-generated text, hallucinated references, or plagiarism.
Summary-reject screen
AAAI's large reviewer pool and high volume mean a desk-level or Phase-1 cut is the most likely way to
lose, so screen for the mechanical failures first.
| Check |
Fast-fail trigger |
Where it bites |
| Page limit |
technical content over the cap |
desk return |
| Anonymity |
author name in PDF, code, or metadata |
policy reject |
| Checklist |
missing or contradictory |
Phase-1 distrust |
| Dual submission |
concurrent archival venue |
ethics reject |
Pre-deadline evidence packet
Build a single review-version packet before the abstract deadline, then refresh it before final
submission. The packet is not a substitute for the official instructions; it is a way to make the
submission audit reproducible and to keep late fixes from creating new policy problems.
| Packet item |
What to capture |
Failure it prevents |
| Policy snapshot |
current conference page, Author Kit, submission instructions, supplementary-material rules, and AI-use policy checked dates |
applying stale AAAI-26 facts to a later cycle |
| PDF proof |
page count, paper size, style file, checklist placement, font/figure warnings, and metadata scrub result |
desk return for formatting or anonymity |
| Author ledger |
OpenReview profiles, conflicts, subject areas, author-limit count, and author-list freeze status |
profile conflict, over-limit author, late author change |
| Supplement ledger |
every appendix, multimedia, code/data ZIP, README, license note, and anonymous link policy decision |
mutable web pointer or identity leak |
| Ethics ledger |
dual-submission status, human-subjects/data constraints, AI-use disclosure, plagiarism/citation check |
policy reject after submission |
For each item, record the evidence path and the person who can fix it. If a rule is uncertain, mark it
as "requires current chair/author-kit confirmation" instead of guessing.
Anonymity sweep order
Run anonymity checks in a fixed order so fixes do not reintroduce leaks:
- PDF text: names, affiliations, acknowledgments, grants, self-identifying project names, and obvious
self-citations.
- PDF metadata: title, author, producer, comments, embedded attachments, and file name.
- References: prior work phrased as "our previous" or "submitted to" when blind citation would be
required.
- Supplement: ZIP names, directory names, notebooks, comments, plots, data paths, license files, and
executable logs.
- External references: GitHub, project pages, anonymous archives, videos, demos, or issue trackers.
- OpenReview metadata: author list, conflicts, subject areas, institutional hints in abstract or
keywords.
The output should separate "must fix before submission" from "acceptable but document why." Do not rely
on a single manual skim; use PDF metadata tools, archive listing, and text search when available.
Worked vignette
A robotics-learning team has 7 strong technical pages but left an acknowledgments line and a GitHub
URL with their lab name in the supplement. The audit flags anonymity as the highest summary-reject
risk: the fix order is strip the acknowledgment, replace the link with an anonymous archive, scrub
ZIP metadata, then re-export and re-run the anonymity sweep before the paper deadline.
Output format
[AAAI readiness] Ready / Needs fixes / Not ready
[Track] Main / AI for Social Impact / AI Alignment / other
[Blocking checks] <page/anonymity/checklist/supplement/author-limit/dual-submission/AI-policy>
[Highest summary-reject risk] <one issue>
[Fix order] <ordered fixes before submission>
Source: brycewang-stanford/Awesome-Journal-Skills → AAAI-Skills/skills/aaai-submission/SKILL.md
1---2name: aaai-submission3description: Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.4---567# AAAI Submission89Use this for an AAAI main technical track submission audit. Reopen the current conference page,10Author Kit, CFP, submission instructions, review process page, supplementary-material page, and11author policies before giving deadline-ready advice.1213## Submission audit1415- Confirm the target track: Main Track, AI for Social Impact, AI Alignment, or another AAAI program.16 Track-specific rules can differ.17- Verify OpenReview account/profile readiness, conflicts, author list, subject areas, and submission18 metadata before the abstract and paper deadlines.19- Check the current AAAI author kit. AAAI-26 submissions used AAAI two-column camera-ready style,20 US Letter PDF, and 7 pages of technical content plus pages solely for references and the21 reproducibility checklist.22- Confirm double-blind compliance in the PDF, file names, references to prior work, supplement,23 code/data, and metadata. Omit acknowledgments in the review version.24- Include the reproducibility checklist after references when current instructions require it.25- Enforce the author submission limit and author-change rules. AAAI-26 limited each author to 1026 combined technical-track submissions and did not allow authors to be added after submission.27- Check multiple-submission compliance. An AAAI submission under review cannot simultaneously be28 under review at another archival venue.29- Apply the current AAAI AI-use policy: editing/polishing author-written text may be allowed, but30 LLM-generated manuscript text, AI authorship, and AI-generated citations are policy risks.3132## Blocking risks3334- Over-limit technical content or malformed PDF.35- Missing reproducibility checklist.36- Identity leakage in paper, supplement, links, code, data, or prior-work citations.37- Author added after the allowed window.38- Concurrent archival submission.39- Web pointers to mutable supplementary material.40- Policy-violating LLM-generated text, hallucinated references, or plagiarism.4142## Summary-reject screen4344AAAI's large reviewer pool and high volume mean a desk-level or Phase-1 cut is the most likely way to45lose, so screen for the mechanical failures first.4647| Check | Fast-fail trigger | Where it bites |48| --- | --- | --- |49| Page limit | technical content over the cap | desk return |50| Anonymity | author name in PDF, code, or metadata | policy reject |51| Checklist | missing or contradictory | Phase-1 distrust |52| Dual submission | concurrent archival venue | ethics reject |5354## Pre-deadline evidence packet5556Build a single review-version packet before the abstract deadline, then refresh it before final57submission. The packet is not a substitute for the official instructions; it is a way to make the58submission audit reproducible and to keep late fixes from creating new policy problems.5960| Packet item | What to capture | Failure it prevents |61| --- | --- | --- |62| Policy snapshot | current conference page, Author Kit, submission instructions, supplementary-material rules, and AI-use policy checked dates | applying stale AAAI-26 facts to a later cycle |63| PDF proof | page count, paper size, style file, checklist placement, font/figure warnings, and metadata scrub result | desk return for formatting or anonymity |64| Author ledger | OpenReview profiles, conflicts, subject areas, author-limit count, and author-list freeze status | profile conflict, over-limit author, late author change |65| Supplement ledger | every appendix, multimedia, code/data ZIP, README, license note, and anonymous link policy decision | mutable web pointer or identity leak |66| Ethics ledger | dual-submission status, human-subjects/data constraints, AI-use disclosure, plagiarism/citation check | policy reject after submission |6768For each item, record the evidence path and the person who can fix it. If a rule is uncertain, mark it69as "requires current chair/author-kit confirmation" instead of guessing.7071## Anonymity sweep order7273Run anonymity checks in a fixed order so fixes do not reintroduce leaks:74751. PDF text: names, affiliations, acknowledgments, grants, self-identifying project names, and obvious76 self-citations.772. PDF metadata: title, author, producer, comments, embedded attachments, and file name.783. References: prior work phrased as "our previous" or "submitted to" when blind citation would be79 required.804. Supplement: ZIP names, directory names, notebooks, comments, plots, data paths, license files, and81 executable logs.825. External references: GitHub, project pages, anonymous archives, videos, demos, or issue trackers.836. OpenReview metadata: author list, conflicts, subject areas, institutional hints in abstract or84 keywords.8586The output should separate "must fix before submission" from "acceptable but document why." Do not rely87on a single manual skim; use PDF metadata tools, archive listing, and text search when available.8889## Worked vignette9091A robotics-learning team has 7 strong technical pages but left an acknowledgments line and a GitHub92URL with their lab name in the supplement. The audit flags anonymity as the highest summary-reject93risk: the fix order is strip the acknowledgment, replace the link with an anonymous archive, scrub94ZIP metadata, then re-export and re-run the anonymity sweep before the paper deadline.9596## Output format9798```text99[AAAI readiness] Ready / Needs fixes / Not ready100[Track] Main / AI for Social Impact / AI Alignment / other101[Blocking checks] <page/anonymity/checklist/supplement/author-limit/dual-submission/AI-policy>102[Highest summary-reject risk] <one issue>103[Fix order] <ordered fixes before submission>104```105106---107108**Source:** [`brycewang-stanford/Awesome-Journal-Skills`](https://github.com/brycewang-stanford/Awesome-Journal-Skills) → `AAAI-Skills/skills/aaai-submission/SKILL.md`
thedixitjain