Pith Number

pith:2FXG3G62

pith:2026:2FXG3G62O4RSG5BAGWT4CI4T65

not attested not anchored not stored refs pending

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

Boheng Zhang, Chunyu Lin, Dewen Fan, Fan Yang, Fei Zuo, Guosheng Lin, Haonan Fan, Honglie Wang, Huaiqing Wang, Huan Ouyang, Jia Sun, Jiuzhou Lin, Jiyuan Wang, Tingting Gao, Yiyang Fan, Yongrui Heng, Zhenlong Yuan, Zijun Li

CaC shows that a hierarchical temporal-then-spatial scan lets vision-language models detect subtle video anomalies more reliably for use as rewards.

arxiv:2605.11723 v2 · 2026-05-12 · 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{2FXG3G62O4RSG5BAGWT4CI4T65}

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

CaC can stably concentrate on subtle anomalies, achieving a 25.7% accuracy improvement on fine-grained anomaly benchmarks and, when used as a reward signal, reduces generated-video anomalies by 11.7% while improving overall video quality.

C2weakest assumption

That the authors' newly constructed generated-video anomaly dataset is sufficiently representative of real deployment distributions and that the added Temporal and Spatial IoU rewards in GRPO training produce generalizable improvements rather than dataset-specific fitting.

C3one line summary

CaC is a hierarchical spatiotemporal concentrating reward model for video anomalies that reports 25.7% accuracy gains on fine-grained benchmarks and 11.7% anomaly reduction in generated videos via a new dataset and GRPO training with temporal/spatial IoU rewards.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools

Receipt and verification

First computed	2026-05-29T02:05:46.618181Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d16e6d9bda772323742035a7c12393f75c84d9ed59c5152933eb1713be7c322d

Aliases

arxiv: 2605.11723 · arxiv_version: 2605.11723v2 · doi: 10.48550/arxiv.2605.11723 · pith_short_12: 2FXG3G62O4RS · pith_short_16: 2FXG3G62O4RSG5BA · pith_short_8: 2FXG3G62

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/2FXG3G62O4RSG5BAGWT4CI4T65 \
  | 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: d16e6d9bda772323742035a7c12393f75c84d9ed59c5152933eb1713be7c322d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fd99ad0981f7740e96478469d14ece693c9119a2593312aac538b19a4c329129",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-12T08:08:33Z",
    "title_canon_sha256": "77d7cc7414059063102e3e5e96fe5eb7b57bdde140cb94450c41d496e33a7a51"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11723",
    "kind": "arxiv",
    "version": 2
  }
}