Pith Number

pith:NOI6RE2B

pith:2026:NOI6RE2BZ5EATX6SOCKGKDR2RZ

not attested not anchored not stored refs resolved

3D Primitives are a Spatial Language for VLMs

Alejandro Mottini, Anping Wang, Arvind Srinivasan, Florian Dubost, Junze Liu, Kai Zhong, Kun Qian, Nan Chen, Qingjun Cui, Sam Zhang, Tian Wang

Vision-language models gain spatial understanding when they reason through 3D geometric primitives written as executable code.

arxiv:2605.12586 v1 · 2026-05-12 · cs.CV · cs.AI · cs.DB

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NOI6RE2BZ5EATX6SOCKGKDR2RZ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

3D geometric primitives (cubes, spheres, cylinders, expressed in executable code) serve as a powerful intermediate representation for spatial understanding.

C2weakest assumption

That gains from Code-CoT and S³-FT stem specifically from the primitive representation rather than general code-generation prompting or fine-tuning effects alone.

C3one line summary

3D geometric primitives in executable code act as an effective intermediate spatial language that boosts VLMs on reconstruction and question-answering tasks.

References

16 extracted · 16 resolved · 6 Pith anchors

[1] The spatial blindspot of vision-language models.arXiv preprint arXiv:2601.09954,

[2] Program Synthesis with Large Language Models · arXiv:2108.07732

[3] Evaluating Large Language Models Trained on Code · arXiv:2107.03374

[4] Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas

[5] SWE-bench: Can Language Models Resolve Real-World GitHub Issues? · arXiv:2310.06770

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:10:01.354139Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6b91e89341cf4809dfd27094650e3a8e5032b5f57e5c9b3dfe9072a365942312

Aliases

arxiv: 2605.12586 · arxiv_version: 2605.12586v1 · doi: 10.48550/arxiv.2605.12586 · pith_short_12: NOI6RE2BZ5EA · pith_short_16: NOI6RE2BZ5EATX6S · pith_short_8: NOI6RE2B

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/NOI6RE2BZ5EATX6SOCKGKDR2RZ \
  | 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: 6b91e89341cf4809dfd27094650e3a8e5032b5f57e5c9b3dfe9072a365942312

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "005ba91da2624f69649f69e4b9af5a4867033ae8696317380337d8fb81c19ecd",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.DB"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-12T17:57:21Z",
    "title_canon_sha256": "adeb545abf459c52b859a0d20949b0c248ca06ee1fafd74c9033433cdffd0be9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12586",
    "kind": "arxiv",
    "version": 1
  }
}