ijcai-related-work — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ijcai-related-work (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 to audit novelty, prior work, and submission eligibility. Reopen the current CFP and submissions FAQ because resubmission and dual-submission rules are policy-sensitive.
with DOI, ISBN, or ISSN.
prepare the required anonymized rejected version and reviews; the response cover letter may be optional depending on current rules.
allowed, but the IJCAI submission itself must remain anonymous.
archival venue during the IJCAI review period.
when current rules require and explain the new technical content.
insufficient, and exactly what is new here.
Because IJCAI spans symbolic AI, search, planning, KR, constraint reasoning, multi-agent, game theory, ML, NLP, and vision, the closest prior work may live in a different subcommunity than the authors'. A reviewer from that adjacent area will know the literature you skipped.
| Prior-work source | Eligibility/anonymity handling | Positioning duty |
|---|---|---|
| Archival proceedings (DOI/ISBN/ISSN) | Cite normally; counts as published | Distinguish your claim from it |
| Non-archival workshop/poster | Usually citable, not a dual-submission bar | Declare if a shorter prior version |
| Author arXiv preprint | Non-anonymous arXiv may be allowed; submission stays anonymous | Cite in third person |
| Recent rejected version (≤12 months) | Prepare anonymized rejected version and reviews | Disclose per current rules |
| Concurrent archival submission | Not permitted during the review period | Resolve before upload |
A bidirectional-search paper cites only recent search venues and omits a closely related planning-community result. An IJCAI planning reviewer flags the gap as a novelty threat. Fix: add the planning result to the closest-works set, state precisely why it does not subsume the new bound, and write a one-sentence novelty contrast a non-search reviewer can verify. If the paper is a shortened version of a prior workshop poster, declare that and describe the added technical content.
IJCAI reviewers cross subcommunities.
resubmission package if a recent rejection exists.
what is new.
[Eligibility] clear / needs declaration / risky
[Closest works] <3-5 items and distinction>
[Resubmission package] <needed/not needed/unknown>
[Dual-submission risk] <none/issues>
[Novelty sentence] <IJCAI-ready contribution contrast>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.