ijcai-topic-selection — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ijcai-topic-selection (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 before writing. IJCAI main-track submissions should report significant, original, previously unpublished AI results with broad relevance to the AI community.
cross-disciplinary AI boundary rather than only reporting an application result.
format, and can survive a two-phase review process with limited response leverage.
or AI and robotics when the venue-specific framing is stronger than a general main-track frame.
expertise.
computer vision, NLP, robotics, HCI, systems, or data mining and a specialist venue has a clearer audience.
data ethics, LLM-use constraints, and in-person presentation feasibility.
IJCAI's edge is breadth and a compact format, but a sharply specialist contribution often finds a clearer audience elsewhere. Route by where the strongest reviewers and framing sit.
| Contribution profile | Strong IJCAI fit | Consider instead |
|---|---|---|
| Cross-cutting AI idea (search, KR, planning, multi-agent) readable across subfields | Yes, main track | — |
| Deep ML theory or representation learning | Sometimes | NeurIPS, ICML, COLT |
| Heavy CV or NLP system | Rarely the best home | CVPR, ACL |
| Mature area survey by established authors | Survey Track | Journal survey |
| Polished, complete result wanting fast journal route | Main track plus AIJ/JAIR ecosystem | — |
| Social-good or human-centered AI framing | Special track | Domain venue |
A mechanism-design result for multi-agent resource allocation could go to an economics-and- computation venue or to IJCAI. If the contribution is an AI technique broadly relevant across agents, search, and learning audiences and fits a compact 7-page body, IJCAI's main track is a strong home; the game-theory/economic-paradigms scope is squarely in-bounds. If the core advance is a fine-grained economic-theory proof aimed at a specialist EC audience, route there instead. Decide by which reviewer pool best judges the central claim.
or route to a domain venue.
specialist venue with a clearer audience.
expertise.
[Fit] strong IJCAI / possible IJCAI / better elsewhere
[Best track] main / special / survey / other venue
[Contribution sentence] <one sentence>
[Top rejection risk] <novelty/clarity/evidence/policy/scope>
[Next action] <experiment, framing, related work, or venue switch>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.