Pith Number

pith:GLKGAV5X

pith:2026:GLKGAV5X7GZ6UH2YYO37LRJV2K

not attested not anchored not stored refs pending

EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

Dingrui Wang, Finn Rasmus Sch\"afer, Johannes Betz, Mattia Piccinini, Sebastian Schmidt, Stephan G\"unnemann, Thomas Stauner, Yuan Gao

Vision-centric foundation models fail to align physical ego-motion concepts with visual observations in autonomous driving.

arxiv:2604.22851 v2 · 2026-04-22 · cs.CV · cs.CL · cs.RO

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GLKGAV5X7GZ6UH2YYO37LRJV2K}

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

This failure persists across model scales and domain-specific training, indicating a structural deficit in how current architectures couple visual perception with physical reasoning. We demonstrate that providing explicit trajectory encodings substantially restores physical consistency across all evaluated models, revealing a functional disentanglement between vision and language: egomotion logic is derived almost exclusively from the language modality, while visual observations contribute negligible additional signal.

C2weakest assumption

The deterministic oracle accurately and unbiasedly maps continuous vehicle kinematics to discrete motion concepts, and the benchmark tasks isolate perception from other model capabilities without introducing confounding factors.

C3one line summary

EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.

Cited by

1 paper in Pith

Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure

Receipt and verification

First computed	2026-07-08T01:19:13.427070Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

32d46057b7f9b3ea1f58c3b7f5c535d29bd03f025b0062d741117e1c65a4537d

Aliases

arxiv: 2604.22851 · arxiv_version: 2604.22851v2 · doi: 10.48550/arxiv.2604.22851 · pith_short_12: GLKGAV5X7GZ6 · pith_short_16: GLKGAV5X7GZ6UH2Y · pith_short_8: GLKGAV5X

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/GLKGAV5X7GZ6UH2YYO37LRJV2K \
  | 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: 32d46057b7f9b3ea1f58c3b7f5c535d29bd03f025b0062d741117e1c65a4537d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3a48833869f746eaac78a46ed321385724be23d5f93032fea15757fc92230924",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-22T07:49:02Z",
    "title_canon_sha256": "a128506afe8c73951c8e331fd6c453891df8ef56af1a64c089f3bee35fb2b36f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.22851",
    "kind": "arxiv",
    "version": 2
  }
}