Pith Number

pith:4KXQSEKC

pith:2026:4KXQSEKCACNIJPCAS2CCXQUMFW

not attested not anchored not stored refs resolved

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models

Dmitry Yudin, Mark Gizetdinov, Vladislav Makarov

SceneGraphVLM generates complete scene graphs from videos in about one second using compact vision-language models and targeted reinforcement learning.

arxiv:2605.13667 v1 · 2026-05-13 · 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{4KXQSEKCACNIJPCAS2CCXQUMFW}

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

With compact VLMs and vLLM-accelerated decoding, SceneGraphVLM achieves a strong quality-speed trade-off, improves precision-oriented SGG metrics while preserving reasonable recall, and generates complete scene graphs with approximately one-second latency.

C2weakest assumption

That the hallucination-aware RL rewards successfully balance coverage and precision on the target benchmarks without introducing new failure modes or requiring dataset-specific tuning that does not generalize.

C3one line summary

SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.

References

48 extracted · 48 resolved · 11 Pith anchors

[1] Qwen3-VL Technical Report 2025 · arXiv:2511.21631

[2] Qwen2.5-vl technical report

[3] Qwen2.5-VL Technical Report · arXiv:2502.13923

[4] Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling 2024 · arXiv:2412.05271

[5] Compile scene graphs with reinforcement learning 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:17.232036Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e2af091142009a84bc4096842bc28c2db62a356946ac6d3cd57d974549e11f2f

Aliases

arxiv: 2605.13667 · arxiv_version: 2605.13667v1 · doi: 10.48550/arxiv.2605.13667 · pith_short_12: 4KXQSEKCACNI · pith_short_16: 4KXQSEKCACNIJPCA · pith_short_8: 4KXQSEKC

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/4KXQSEKCACNIJPCAS2CCXQUMFW \
  | 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: e2af091142009a84bc4096842bc28c2db62a356946ac6d3cd57d974549e11f2f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d07ffdb47a3c956d7a68e5aaa76b132c5c7815a7172b31fcc35853cc1d19a574",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T15:27:41Z",
    "title_canon_sha256": "f04ec2be006a9833106289e9936921d6238aa3883a63199fe5bc8268919a8873"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13667",
    "kind": "arxiv",
    "version": 1
  }
}