ijcai-submission — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ijcai-submission (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.
Use this for an IJCAI main-track submission audit. Reopen the current conference CFP, Author Kit, FAQ, reproducibility page, submission site, and conflict policy before giving deadline-ready advice.
non-main program. Track rules and deadlines can differ.
author confirmations, keywords, conflicts, and any Primary Paper Initiative fee exposure.
7 pages for body text, figures, and tables, plus up to 2 pages for references.
version, and that the optional ethics statement sits where current rules permit.
paths, URLs, and resubmission files.
not rely on rebuttal-time uploads.
rejection disclosure before upload.
allowed, but LLM-written manuscript text was a desk-reject risk.
IJCAI screens a large submission volume and can reject on mechanical grounds before any scientific review. Sort each risk by whether it is auto-fatal at intake.
| Risk | Severity | Pre-upload check |
|---|---|---|
| Missing abstract registration | Fatal | Abstract filed by its earlier deadline |
| Overlength or template manipulation | Fatal | Page count and Author Kit style verified |
| Anonymity leak in PDF/metadata/code | Fatal | Names, URLs, filenames scrubbed |
| Missing resubmission file | Fatal | Anonymized rejected version attached |
| Concurrent archival submission | Fatal | No venue overlap during review |
| LLM-written manuscript text | High | Only policy-allowed polishing |
A multi-agent RL paper is ready scientifically but its anonymized PDF embeds the lab name in a figure caption and its code ZIP keeps an institutional path. Both are anonymity leaks that can desk-reject the paper before review. Fix order: scrub the caption and metadata, re-zip with relative paths, confirm the page count, verify the abstract was registered on time, and confirm no concurrent archival submission.
shrink margins, fonts, or spacing to fake compliance.
[IJCAI readiness] Ready / Needs fixes / Not ready
[Track] main / special / survey / other
[Blocking checks] <page/anonymity/authors/ORCID/supplement/resubmission/dual-submission/LLM>
[Highest desk-reject risk] <one issue>
[Fix order] <ordered fixes before submission>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.