Pith Number

pith:77QQMSS5

pith:2026:77QQMSS5FRQYDV327AZ7TPRXLF

not attested not anchored not stored refs resolved

GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language

Huishuai Zhang, Jinwoong Kim, Rui Yang

Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems.

arxiv:2605.13167 v1 · 2026-05-13 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{77QQMSS5FRQYDV327AZ7TPRXLF}

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

despite reasonable success rates, models frequently exhibit structural hallucinations, missing objects, and failures to satisfy geometric constraints, with limited ability to exploit visual and constraint-based feedback for self-correction

C2weakest assumption

The 489 problems are text-complete and constructible after automated filtering and human validation, and the chosen DSL accurately represents valid geometric constructions.

C3one line summary

GeoBuildBench is a new benchmark requiring LLMs to generate executable geometry constructions from text, revealing frequent hallucinations, missing objects, and constraint failures in state-of-the-art models.

References

12 extracted · 12 resolved · 1 Pith anchors

[1] Qwen3-VL Technical Report 2021 · arXiv:2511.21631

[2] One definition per label

[3] Construct, don't assert

[4] These prompts define the construction suitability criteria and the formal extraction of geometric objects and verifica- tion conditions

[5] Determine whether this problem is suitable for geometric figure construction

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction

Receipt and verification

First computed	2026-05-18T03:08:56.699362Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0

Aliases

arxiv: 2605.13167 · arxiv_version: 2605.13167v1 · doi: 10.48550/arxiv.2605.13167 · pith_short_12: 77QQMSS5FRQY · pith_short_16: 77QQMSS5FRQYDV32 · pith_short_8: 77QQMSS5

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/77QQMSS5FRQYDV327AZ7TPRXLF \
  | 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: ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8410ba2e2f49ddb32a3ad7c2f86c3c449830c77be08fe23d70ff257fbc11e2ee",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T08:30:12Z",
    "title_canon_sha256": "7804e664a040037fee66e7b338add73f19f91fd4e634549dd42f0e595308920d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13167",
    "kind": "arxiv",
    "version": 1
  }
}