Use when reasoning about the ACM MM (ACM Multimedia) review pipeline — thematic-area routing to reviewers and area chairs, the OpenReview double-blind process and its single-blind track exceptions, the optional anonymous rebuttal, the meta-review and decision, and the oral/poster and award tiers, and where an author actually has leverage.
SkillScore83Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 20 of 24 test cases with the skill, and 12 of 24 without it.
Without skill50%
With skill83%
Checks it passed that the model alone missed
Formats the output using the tag [Next action].
Formats the output using the tag [Area routing].
Formats the output using the tag [Review split].
and 11 more in the full report
9 fixed11 passed either way3 still failing1 broke
Pass-rate lift
+33 pp
Tokens
+13%
Agent turns
0%
Response time
-36%
Model gemini-3.6-flashMeasured 8/15/2026v120 of 24 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
An author submitting a paper to the ACM MM Reproducibility Track wants to know if they must anonymize their repository link and remove author names from their submission.
What was checked, without and with the skill
Checked
Without skill
With skill
States that the Reproducibility Track uses single-blind reviewing.
Missed
Passed
case-18 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md86 linessingle file
ACM MM Review Process
Use this to build an accurate mental model of how an ACM Multimedia paper is judged, so
strategy targets the points where an author can move the outcome and not the points where they
cannot.
The pipeline
Submission + thematic area. The paper enters OpenReview under a chosen thematic area,
which routes it to a matching reviewer pool and area chair.
Assignment. Reviewers and an AC are assigned; a mismatched thematic area is where papers
get reviewers who cannot judge the contribution.
Reviews. Reviewers assess novelty, cross-modal soundness, evidence (including user
studies where relevant), and reproducibility.
Rebuttal. An optional, anonymous author response addresses reviews; new external
links are not allowed.
Discussion + meta-review. Reviewers and the AC discuss; the AC writes a meta-review and
recommendation.
Decision + tiers. Accept/reject, with accepted papers sorted into presentation tiers
(oral vs. poster) and award consideration.
Where leverage exists
Stage
Author leverage
Reality
Thematic-area choice
High
You pick who reviews you — choose the area that can judge the contribution
Submission quality
High
The paper is the main lever; the rebuttal only patches
Rebuttal
Medium
Fix factual errors and add small confirmatory results; rarely flips a strong reject
Discussion
Low/indirect
You cannot see it; a clean rebuttal gives the AC ammunition
Decision/tiers
None directly
Set by AC/PC after discussion
Reading a review set
Separate factual errors (a reviewer misread a result) from judgment (they find the
delta small); the first is fixable in rebuttal, the second usually is not.
Weight the cross-modal critiques: "the fusion is not shown to matter" is often the
decisive line, and an ablation is the answer.
Note the AC's implicit questions in the meta-review; that is who the rebuttal is really
written for.