Pith Number

pith:VQBYAW5A

pith:2026:VQBYAW5ALV6XF6WIYUYBIZKO5R

not attested not anchored not stored refs resolved

MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation

Oana Ignat, Parth Bhalerao, Shuowei Li, Yuming Zhao

Multi-agent refinement of text prompts raises cultural fidelity in generated videos.

arxiv:2605.16716 v1 · 2026-05-16 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VQBYAW5ALV6XF6WIYUYBIZKO5R}

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

Multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency.

C2weakest assumption

That decomposing prompts into person, action, and location dimensions and assigning them to specialized agents will reliably increase cultural fidelity without introducing new inconsistencies or biases that the chosen metrics fail to detect.

C3one line summary

MAVEN is a multi-agent prompt refinement framework that improves cultural fidelity in text-to-video generation, demonstrated on a new benchmark of 243 prompts and 972 videos across Chinese, American, and Romanian cultures.

References

21 extracted · 21 resolved · 2 Pith anchors

[1] SimCityNet: Quanti- fying Geo-Cultural bias in AI-generated urban videos through interpretable scene embeddings. SSRN. Ac- cessed 2025-10-10. Yubin Chen, Xuyang Guo, Zhenmei Shi, Zhao Song, and Jiahao 2025

[2] Google DeepMind

[3] The Llama 3 Herd of Models · arXiv:2407.21783

[4] Storyagent: Customized storytelling video generation via multi-agent collaboration

[5] Sam Ade Jacobs, Masahiro Tanaka, Chengming Zhang, Minjia Zhang, Shuaiwen Leon Song, Samyam Rajbhandari, and Yuxiong He

Receipt and verification

First computed	2026-05-20T00:02:38.116117Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62

Aliases

arxiv: 2605.16716 · arxiv_version: 2605.16716v1 · doi: 10.48550/arxiv.2605.16716 · pith_short_12: VQBYAW5ALV6X · pith_short_16: VQBYAW5ALV6XF6WI · pith_short_8: VQBYAW5A

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/VQBYAW5ALV6XF6WIYUYBIZKO5R \
  | 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: ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8a7609e0d0ec8f464314d08bda316e7f85971cb4b352f29f3b11655349af9923",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T00:01:18Z",
    "title_canon_sha256": "c941abc9879edb168c4ecce86a628b9baa3de91ef7268649d876e03dde1053bd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16716",
    "kind": "arxiv",
    "version": 1
  }
}