Pith Number

pith:4FJ3YBJJ

pith:2026:4FJ3YBJJDNDFGB45VKWDT23VRG

not attested not anchored not stored refs pending

How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study

Johannes Betz, Mattia Piccinini, Roberto Brusnicki

Vision-language models reach only 57% accuracy on sequential driving scenes and fall short of human performance.

arxiv:2604.06750 v2 · 2026-04-08 · 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{4FJ3YBJJDNDFGB45VKWDT23VRG}

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

even top models achieve only 57% accuracy, not matching human performance in similar constraints (65%) and exposing significant capability gaps. Our analysis shows that VLMs excel with static object detection but struggle with understanding the vehicle dynamics and temporal relations.

C2weakest assumption

That the custom-generated questions and extracted sequences from existing driving videos provide an unbiased and representative test of sequential understanding without introducing artifacts from the extraction or question-generation process.

C3one line summary

VENUSS benchmark shows top VLMs achieve 57% accuracy on sequential driving scenes, strong on static objects but weak on vehicle dynamics and temporal relations.

Receipt and verification

First computed	2026-05-21T01:05:18.644949Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e153bc05291b4653079daaac39eb75899bcd53acda9c7b02fb8d934ec98e4832

Aliases

arxiv: 2604.06750 · arxiv_version: 2604.06750v2 · doi: 10.48550/arxiv.2604.06750 · pith_short_12: 4FJ3YBJJDNDF · pith_short_16: 4FJ3YBJJDNDFGB45 · pith_short_8: 4FJ3YBJJ

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/4FJ3YBJJDNDFGB45VKWDT23VRG \
  | 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: e153bc05291b4653079daaac39eb75899bcd53acda9c7b02fb8d934ec98e4832

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "eaae9699e0bf05d1707f27b6b80d1def58d430e7ddedfb235e2797a3263dc91c",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-08T07:14:55Z",
    "title_canon_sha256": "67f334d6da57a1375949c60affdc945fb1c3272c0f806c570259df75d3a88255"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.06750",
    "kind": "arxiv",
    "version": 2
  }
}