Pith Number

pith:XMXDSXED

pith:2026:XMXDSXEDPTLLBOKOQT6QPPVH25

not attested not anchored not stored refs resolved

COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection

Darryl Cherian Jacob, Kai Wang, Pan He, Xinyu Liu

COPRA uses reinforcement learning to generate input-specific parameter updates that dynamically adapt a frozen vision-language model to each video segment for anomaly detection.

arxiv:2605.15325 v1 · 2026-05-14 · 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{XMXDSXEDPTLLBOKOQT6QPPVH25}

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

COPRA generates input-specific parameter updates to dynamically adapt a frozen VLM for each video segment during both training and inference, consistently outperforming static baselines in both in-domain and cross-domain settings and generalizing to unseen tasks such as multiple-choice Video Question Answering and Dense Captioning.

C2weakest assumption

That reinforcement learning can stably and effectively produce useful input-conditioned parameter updates for a frozen VLM without requiring domain-specific hyperparameter search or suffering from instability when applied to new video distributions.

C3one line summary

COPRA introduces conditional parameter adaptation via RL to dynamically tune frozen VLMs for video anomaly detection, outperforming static methods in in-domain and cross-domain settings while generalizing to other video tasks.

References

64 extracted · 64 resolved · 2 Pith anchors

[1] Unlocking vision-language models for video anomaly detection via fine-grained prompting , author=. WACV , pages=

[2] Real-world anomaly detection in surveillance videos , author=. CVPR , pages=

[3] Workshop on Neural Network Weights as a New Data Modality , year=

[4] Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks , author=. CVPR , pages=

[5] A Survey of Weight Space Learning: Understanding, Representation, and Generation , author=. 2026 , eprint= 2026

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:52.732906Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bb2e395c837cd6b0b94e84fd07bea7d74e2d89674bc99a7130a7634b0eceafd6

Aliases

arxiv: 2605.15325 · arxiv_version: 2605.15325v1 · doi: 10.48550/arxiv.2605.15325 · pith_short_12: XMXDSXEDPTLL · pith_short_16: XMXDSXEDPTLLBOKO · pith_short_8: XMXDSXED

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/XMXDSXEDPTLLBOKOQT6QPPVH25 \
  | 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: bb2e395c837cd6b0b94e84fd07bea7d74e2d89674bc99a7130a7634b0eceafd6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0193d3fc29c3f044cdd902aae0c909281da8816d4d33468cee0b29c715566720",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T18:39:40Z",
    "title_canon_sha256": "9fb6019da126079b02b8937f97646fd00ef4007e0966a848ebdb95701d8802ed"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15325",
    "kind": "arxiv",
    "version": 1
  }
}