Pith Number

pith:FWUC24DS

pith:2026:FWUC24DSCS5W4EW3BQCE2FKWFQ

not attested not anchored not stored refs resolved

Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction

Jinjia Zhou, Shuliang Zhu, Tomiwa Adey

Appending a coarse four-group semantic color code to raw point attributes before tokenization improves LLM-based structured indoor prediction while leaving the decoder unchanged.

arxiv:2605.16832 v1 · 2026-05-16 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FWUC24DSCS5W4EW3BQCE2FKWFQ}

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

The semantic color code is appended to the original raw point attributes before tokenization, so geometry and semantics share the same sparse tokenization path while the downstream language model decoder and output serialization remain unchanged.

C2weakest assumption

That reliable coarse semantic evidence (furniture/walls/openings/others) can be obtained from RGB or other sources and injected without introducing errors that outweigh the benefits after sparse pooling and LLM decoding.

C3one line summary

Coarse four-group semantic color coding (RGBB) appended to point clouds before tokenization improves LLM-based structured indoor prediction on Structured3D, SpatialLM, and ARKitScenes, especially for openings and furniture instances.

References

48 extracted · 48 resolved · 0 Pith anchors

[1] Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

[2] Wang, Shuzhe and Leroy, Vincent and Cabon, Yohann and Chidlovskii, Boris and Revaud, Jerome , booktitle=

[3] Grounding image matching in 2024

[4] Wang, Jianyuan and Chen, Minghao and Karaev, Nikita and Vedaldi, Andrea and Rupprecht, Christian and Novotny, David , booktitle=

[5] Nie, Yinyu and Han, Xiaoguang and Guo, Shihui and Zheng, Yujian and Chang, Jian and Zhang, Jian Jun , booktitle=

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:25.096709Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2da82d707214bb6e12db0c044d15562c04dc1875b7f1195661121332e9d3100d

Aliases

arxiv: 2605.16832 · arxiv_version: 2605.16832v1 · doi: 10.48550/arxiv.2605.16832 · pith_short_12: FWUC24DSCS5W · pith_short_16: FWUC24DSCS5W4EW3 · pith_short_8: FWUC24DS

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/FWUC24DSCS5W4EW3BQCE2FKWFQ \
  | 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: 2da82d707214bb6e12db0c044d15562c04dc1875b7f1195661121332e9d3100d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9e7c972760fa532a9f5c6ecb62c24d81ef8430603f01148371aba0795b810e97",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T06:28:23Z",
    "title_canon_sha256": "1fe06f09205860adb2554dde281a7774eac692126f075d5c1891217e1a6ee109"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16832",
    "kind": "arxiv",
    "version": 1
  }
}