pith. sign in
Pith Number

pith:YNQJL4CM

pith:2026:YNQJL4CMKFECWAPFYQ6KXDPJKD
not attested not anchored not stored refs pending

Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark

Chao Li, Chenglam Ho, Hao Chen, Jinping Wang, Seng Nam Chen, Xinyu Mao, Yu Zhang

Vision-language models forget long-range scene context in videos, shown by a new benchmark with sharp accuracy drops.

arxiv:2603.27259 v3 · 2026-03-28 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{YNQJL4CMKFECWAPFYQ6KXDPJKD}

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

Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context.

C2weakest assumption

That the authors' definition of a scene as a coherent segment with consistent visual and semantic contexts accurately isolates long-range forgetting, and that the benchmark questions do not introduce other confounds in video selection or question design.

C3one line summary

SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.

Receipt and verification
First computed 2026-06-23T01:12:04.172364Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

c36095f04c51482b01e5c43cab8de950e4981d45e47e73177019011181475703

Aliases

arxiv: 2603.27259 · arxiv_version: 2603.27259v3 · doi: 10.48550/arxiv.2603.27259 · pith_short_12: YNQJL4CMKFEC · pith_short_16: YNQJL4CMKFECWAPF · pith_short_8: YNQJL4CM
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD \
  | 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: c36095f04c51482b01e5c43cab8de950e4981d45e47e73177019011181475703
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "9b4a89f2c7c43f0f960d61d77cc48477fdefe91ef8f2eef88e3cedeea7cb2d5c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-03-28T12:44:19Z",
    "title_canon_sha256": "3ca3f6151f7d08480faf12c4676262d71303d8b81b2330b5e919c0d9e9c76115"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.27259",
    "kind": "arxiv",
    "version": 3
  }
}