pith:LG5OKHXJ
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly.
arxiv:2605.09883 v2 · 2026-05-11 · cs.CV · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LG5OKHXJGHRS7B2ZX5RDKTUBVF}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
frontier models achieving 70--83% on Cartesian layouts collapse to 31--39% on Polar equivalents, with degradation persisting even under complete logical equivalence.
Re-formulating the 53 tasks in polar coordinates preserves identical logical constraints, task semantics, and difficulty levels without introducing unrelated visual or reasoning challenges.
MLLMs scoring 70-83% on Cartesian visual tasks drop to 31-39% on logically equivalent polar versions, exposing reliance on grid discretization shortcuts instead of topology-invariant reasoning.
Formal links
Receipt and verification
| First computed | 2026-06-02T01:03:48.359039Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "d3ad5e1b5375361286f17b144713d09ba955fb5529b0bd13e7561262516f1bb1",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-11T02:16:48Z",
"title_canon_sha256": "cae32c8f94241fd2acec258b15935b72ecb8b85a67d2e53c2bb0a1d973c3da9c"
},
"schema_version": "1.0",
"source": {
"id": "2605.09883",
"kind": "arxiv",
"version": 2
}
}