Pith Number

pith:USFK5FKN

pith:2026:USFK5FKNNWCJNRFI2TAMB26TKW

not attested not anchored not stored refs resolved

Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models

Anoop Cherian, Furkan Mumcu, Michael J. Jones, Yasin Yilmaz

Video anomaly detection research has shifted to multi-scene LLM models that reduce the task to semantic category recognition rather than scene-specific normality.

arxiv:2605.12725 v1 · 2026-05-12 · 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{USFK5FKNNWCJNRFI2TAMB26TKW}

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

meaningful progress in VAD requires renewed focus on single-scene, spatially-aware, and explainable formulations that capture the nuanced structure of normality within individual environments.

C2weakest assumption

Real-world video anomaly detection is typically performed within a single scene where normality is determined by local geometry, semantics, and activity patterns.

C3one line summary

Video anomaly detection is misframed by multi-scene LLM models that reduce the task to semantic action recognition instead of capturing local scene normality, requiring a return to single-scene spatially-aware methods.

References

57 extracted · 57 resolved · 1 Pith anchors

[1] A coarse-to-fine pseudo-labeling (c2fpl) framework for unsupervised video anomaly detection 2024

[2] Collab- orative learning of anomalies with privacy (clap) for unsupervised video anomaly detection: A new base- line 2024

[3] Advancing video anomaly detection: A concise review and a new dataset 2024

[4] Prompt-enhanced multiple instance learning for weakly supervised video anomaly detec- tion 2024

[5] Generalizing single-frame supervi- sion to event-level understanding for video anomaly detection 2025

Receipt and verification

First computed	2026-05-18T03:09:49.336088Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a48aae954d6d8496c4a8d4c0c0ebd3558ff2d098387d261e8428d23b3663cbc7

Aliases

arxiv: 2605.12725 · arxiv_version: 2605.12725v1 · doi: 10.48550/arxiv.2605.12725 · pith_short_12: USFK5FKNNWCJ · pith_short_16: USFK5FKNNWCJNRFI · pith_short_8: USFK5FKN

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/USFK5FKNNWCJNRFI2TAMB26TKW \
  | 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: a48aae954d6d8496c4a8d4c0c0ebd3558ff2d098387d261e8428d23b3663cbc7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "471d9ea74ff0f314fee16cdba331d8c1dab9a82002292f91316c9f8033fe1cdb",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-12T20:29:49Z",
    "title_canon_sha256": "d998bcd8018cc4e0b9a433f571ccb287d1fce6cbde7b10b0703d703b5c831743"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12725",
    "kind": "arxiv",
    "version": 1
  }
}