pith:VIAW4PMP
2.5-D Decomposition for LLM-Based Spatial Construction
A 2.5-D decomposition lets LLMs build structures from language instructions by planning only the horizontal plane while a deterministic executor computes vertical placements from column occupancy.
arxiv:2605.07066 v2 · 2026-05-08 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{VIAW4PMPOHYVVJYYTWBK3JH7F5}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
On the Build What I Mean benchmark (160 rounds), GPT-4o-mini with this pipeline achieves 94.6% mean structural accuracy across 12 independent runs, within 3.0 percentage points of the 97.6% ceiling imposed by architect-agent errors that no builder-side improvement can address. This outperforms both GPT-4o at 90.3% and the best competing system at 76.3%.
That vertical block placements are fully and correctly determined solely by column occupancy without requiring additional spatial reasoning or handling complex inter-block dependencies beyond simple stacking.
2.5-D decomposition lets LLMs achieve 94.6% structural accuracy on a building benchmark by handling only horizontal planning while a symbolic system manages vertical placements from occupancy.
Receipt and verification
| First computed | 2026-05-20T01:06:09.882679Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
aa016e3d8f71f15aa7189d82ada4ff2f70492113faeb61831650fef2c777bd7e
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/VIAW4PMPOHYVVJYYTWBK3JH7F5 \
| 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: aa016e3d8f71f15aa7189d82ada4ff2f70492113faeb61831650fef2c777bd7e
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "1542e9f7a33f4ca5981b4c90c26d920c3faa5a066e154bd717d7e16a69cc286a",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-08T00:17:33Z",
"title_canon_sha256": "5b529320c8728de9af002b36202f427c6b3259fc19b53fdeb0e86748b126dabe"
},
"schema_version": "1.0",
"source": {
"id": "2605.07066",
"kind": "arxiv",
"version": 2
}
}