Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/cav-submission
Use when auditing a CAV (Computer Aided Verification) submission for portal readiness, covering the four submission categories (Regular / Short Tool / Short Application / Industrial Experience & Case Studies), the LNCS page limits, the per-category anonymization matrix, the artifact-intent declaration, and desk-reject triage before the AoE paper deadline.
Passed 20 of 22 test cases with the skill, and 12 of 22 without it.
and 6 more in the full report
8 fixed12 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our technical contribution draft for CAV is 17 pages of main exposition, followed by 3 pages of references and a 4-page technical appendix. Does this manuscript exceed the page allowance for a Regular Paper submission?
| Checked | Without skill | With skill |
|---|---|---|
| The answer confirms the main text fits within the 18-page limit because references and appendices are excluded from the page count | Missed | Passed |
The instructions your model reads when the skill loads.
Run this audit before uploading to the CAV submission portal. CAV research papers are published
open access as Springer LNCS chapters, and the submission is judged by a two-stage review, so
the category you pick, the LNCS format, and the anonymization rule for that category all have to be
right before the deadline. Every number below was read from the CAV 2026 Call for Papers on
2026-07-09 via search renderings of the i-cav.org URLs (see
resources/official-source-map.md); treat them as a one-cycle snapshot and reopen the live CFP
first.
CAV 2026 solicits four categories, and the category sets both the page limit and the anonymity rule:
| Category | Page limit (LNCS, excl. refs + appendix) | Anonymized? | Fits |
|---|---|---|---|
| Regular Paper | 18 pages | Yes (double-blind) | A new technique/algorithm with a formal contribution |
| Short Tool Paper | 10 pages | No | A usable, downloadable verification tool on standard benchmarks |
| Short Application Paper | 10 pages | Yes (double-blind) | Applying verification to a concrete problem/system |
| Industrial Experience Report & Case Study | 10 pages | No | A real-world/industrial verification experience |
The anonymization split is unusual and cycle-volatile — verify it on the current CFP. The logic: a tool paper that hid its tool's name would be unreviewable, so tool and industrial papers are not anonymized; regular and application papers are.
llncs document class, single column, unmodified. This is the Springer path — do not
carry an ACM acmart or an IEEEtran double-column habit across from a sibling venue.cav-supplementary).llncs; recover space by editing, not by tampering with
the template.For the anonymized categories, CAV runs double-blind review, and verification papers leak identity through tool names, repositories, and benchmark artifacts:
test cases passed, vs 12 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.