Use when interpreting the ACM CHI Papers review pipeline — 1AC and 2AC roles, the A/ARR/RR/RRX/X recommendation scale, desk-reject and rubric-based assisted desk-reject screening, the revise-and-resubmit threshold, round-2 PC decisions — and what each stage means for authors.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 21 of 22 test cases with the skill, and 12 of 22 without it.
Without skill55%
With skill95%
Checks it passed that the model alone missed
Lists the five scale values as A, ARR, RR, RRX, and X.
Names ADR-Data as the rubric ground for insufficient data.
Cites approximately 65% as the resubmission acceptance rate benchmark.
and 7 more in the full report
9 fixed12 passed either way1 still failing0 broke
Pass-rate lift
+41 pp
Tokens
+28%
Agent turns
0%
Response time
-41%
Model gemini-3.6-flashMeasured 8/15/2026v121 of 22 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
What are the five official recommendation acronyms/labels on the CHI round-1 review scale?
What was checked, without and with the skill
Checked
Without skill
With skill
Lists the five scale values as A, ARR, RR, RRX, and X.
Missed
Passed
case-20 · 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.md104 linessingle file
CHI Review Process
CHI's Papers track runs a two-round, committee-anchored process that resembles a
journal's revise-and-resubmit more than an ML conference's rebuttal. Mechanics below
follow the CHI 2027 and CHI 2026 Papers Review Process pages and the CHI 2026
outcome reports (read 2026-07-08 via search renderings; the conference sites block
direct automated fetching).
Who touches your paper
1AC — the Associate Chair who manages your submission: screens it, recruits two
external reviewers, writes the meta-review, and represents the paper at the PC
meeting. The 1AC is your most important reader at CHI.
2AC — a second committee member who writes a full review like the externals.
Two external reviewers — recruited by the 1AC for topical expertise.
Subcommittee chairs (SCs) — run the subcommittee you designated, arbitrate desk
rejects with the ACs, and chair the discussions.
Papers Chairs / PC — own the overall process and the final accept list.
Two kinds of early rejection
CHI screens before full review, and since the 2026 cycle this screening has teeth:
Desk reject (DR): format and compliance — wrong template, anonymization
failure, unjustified length (the >12,000-word rule), policy violations.
Assisted desk reject (ADR): a rubric-based judgment call made jointly by SCs
and ACs, introduced for CHI 2026 and codified by the CHI Steering Committee. The
four posted rubric grounds:
Rubric code
Meaning
ADR-Context
Grossly insufficient literature review to contextualize the contribution
ADR-Contribution
Disproportionately small HCI contribution for the paper's length
ADR-Data
Grossly insufficient data to support the claims
ADR-Method
Grossly insufficient methodological detail, conceptual clarity, or research transparency
At CHI 2026, subcommittees desk-rejected between 1.4% and 17.9% of their submissions
and assisted-desk-rejected between 1.1% and 16.6%, with ADR-Context the most common
rubric ground — weak related work is now a pre-review rejection risk, not just a
score penalty (chi-related-work).