ijcai-review-process — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ijcai-review-process (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 reason about review-stage strategy. Reopen the current CFP, FAQ, peer-review principles, and conflict policy before making process claims.
with two good-quality but insufficiently positive reviews could receive summary rejection without author response.
with AC coordination and SAC cross-checking.
not a dialogue with reviewers.
current grants/projects, sponsorship, personal relationships, or animosity under the IJCAI COI policy.
submission confidentiality.
| Stage | Who decides | Author leverage | Forbidden |
|---|---|---|---|
| Phase 1 summary reject | Two PC reviewers, AC | None: there is usually no response here | Treating phase 1 as if a rebuttal will save it |
| Full review | PC, SPC, AC discussion | Concise response on pressing questions and factual errors | New experiments, code links, or scope changes |
| Decision | AC recommends, SAC cross-checks, chairs finalize | Clarity already in the paper, ethics flags resolved | Contacting or guessing reviewer identity |
| Ethics escalation | Ethics Chair | Confidential channel for unethical-review concerns | Using ethics box to argue scores |
Because IJCAI spans many AI subcommunities, a paper can draw one in-area and one out-of-area reviewer; the out-of-area reviewer is often where summary-reject risk concentrates, so the phase-1 readability of the contribution matters more than at single-topic venues.
A constraint-reasoning paper gets two competent reviews that are lukewarm because the second reviewer, from a learning background, could not locate the contribution by page two. Under IJCAI rules this profile is a summary-reject candidate before any response. The leverage is not in the rebuttal: it is in writing so a non-specialist PC member sees the novel claim on page one. Diagnose this risk pre-submission, since phase 1 may give no chance to reply.
response with a pointer to the submitted section; do not relitigate the score.
fix readability upstream; you cannot count on a response stage.
through the official channel only.
[Current stage] submitted / phase 1 / full review / response / decision
[Decision actors] <PC/SPC/AC/SAC/chairs>
[Likely leverage] <paper clarity / factual correction / ethics / reproducibility>
[Forbidden moves] <contact reviewers / new results / identity leakage>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.