aaai-related-work — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited aaai-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 make the novelty claim robust under AAAI's broad AI review. The related-work section must help reviewers distinguish the paper from both archival work and contemporaneous non-archival work.
expectations.
evidence, scope, and contribution.
Use this structure:
Closest prior work solves <problem> under <assumptions>.
It does not address <specific missing setting/mechanism/evidence>.
This paper contributes <new item> and verifies it through <evidence>.
The claim is limited to <scope>.AAAI spans search, planning, knowledge representation, constraint satisfaction, multi-agent systems, learning, NLP, vision, and robotics, so the closest prior work may live in a subfield your reviewer does not. Make the contrast explicit for a non-specialist instead of assuming shared background.
| Neighbor venue | Reviewer expectation | Differentiation to spell out |
|---|---|---|
| IJCAI | broad-AI overlap | what your result adds beyond their framing |
| NeurIPS/ICML | ML method or theory depth | why AAAI breadth, not just a benchmark gain |
| ICLR | representation-learning lens | non-learning mechanism or guarantee you contribute |
| AAAI prior years | incremental-track suspicion | the new assumption, evidence, or scope |
and name the specific setting or evidence you add; do not bury or ignore it.
substantially similar work is under review elsewhere, satisfying the dual-submission rule.
AI systems as citable scientific sources and hallucinated citations are a credibility risk.
A reasoning-over-knowledge-graphs paper sits near both a KR archival line and a recent NeurIPS embedding paper. Using the axes: against KR work the difference is evidence (learned vs. hand-built rules); against the NeurIPS neighbor it is scope (logical soundness, not just link prediction). One contemporaneous arXiv preprint is cited as non-archival with a one-line delta, and the dual-submission box is checked clean.
[Closest work] <paper/system/benchmark>
[Difference axis] problem / method / theory / data / evaluation / system / impact
[Must-cite items] <archival and contemporaneous work>
[Multiple-submission risk] none / clarify / withdraw / reroute
[Revision text] <AAAI-ready related-work paragraph>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.