Pith Number

pith:OP2TOXD6

pith:2026:OP2TOXD63V2HB5TBGX5FRRLE46

not attested not anchored not stored refs pending

Are Video Reasoning Models Ready to Go Outside?

Changgyu Boo, Jaehong Yoon, Yangfan He

A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances.

arxiv:2603.10652 v3 · 2026-03-11 · 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{OP2TOXD63V2HB5TBGX5FRRLE46}

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

ROVA effectively mitigates performance degradation, boosting relative accuracy by at least 24% and reasoning by over 9% compared with baseline models (QWen2.5/3-VL, InternVL2.5, Embodied-R). These gains transfer to clean standard benchmarks, yielding consistent improvements.

C2weakest assumption

That the specific spatio-temporal corruptions injected into PVRBench faithfully represent the distribution of real-world disturbances and that the self-reflective difficulty estimation does not introduce systematic bias in sample selection.

C3one line summary

ROVA boosts video reasoning model accuracy by at least 24% and reasoning by over 9% under realistic perturbations via a new consistency reward and adaptive training, while PVRBench reveals up to 35% drops in existing models.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

Receipt and verification

First computed	2026-07-01T01:17:48.687067Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e

Aliases

arxiv: 2603.10652 · arxiv_version: 2603.10652v3 · doi: 10.48550/arxiv.2603.10652 · pith_short_12: OP2TOXD63V2H · pith_short_16: OP2TOXD63V2HB5TB · pith_short_8: OP2TOXD6

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/OP2TOXD63V2HB5TBGX5FRRLE46 \
  | 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: 73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7b1e4d5cea334d2d13283ac45944e98fd4c1fe83dc2a752bb678dcae2aaf8b65",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-03-11T11:10:52Z",
    "title_canon_sha256": "88143994ffd17a5f2b1fdd0f1f3e61baa2d6281017b712fcdae67546a70be854"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.10652",
    "kind": "arxiv",
    "version": 3
  }
}