Pith Number

pith:2JPMMZB4

pith:2026:2JPMMZB45P2RPTO3YBL24CA64V

not attested not anchored not stored refs pending

Do Joint Audio-Video Generation Models Understand Physics?

Chenming Ge, Feiyu Du, Hao Fang, Jiageng Liu, Mingwei Xu, Shijian Deng, Weiguo Pian, Xiulong Liu, Yapeng Tian, Zexin Xu, Zijun Cui

Joint audio-video generation models generate plausible content but fail to maintain real-world physical consistency across transitions.

arxiv:2605.07061 v2 · 2026-05-08 · cs.SD · cs.AI · cs.CV · cs.MM

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{2JPMMZB45P2RPTO3YBL24CA64V}

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

Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts.

C2weakest assumption

That the five evaluation dimensions (visual/audio semantic adherence, visual/audio physical commonsense, cross-modal physical commonsense) together constitute a sufficient and unbiased measure of physical understanding without requiring additional human validation or external physics simulators.

C3one line summary

Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-02T01:03:48.229439Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4

Aliases

arxiv: 2605.07061 · arxiv_version: 2605.07061v2 · doi: 10.48550/arxiv.2605.07061 · pith_short_12: 2JPMMZB45P2R · pith_short_16: 2JPMMZB45P2RPTO3 · pith_short_8: 2JPMMZB4

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/2JPMMZB45P2RPTO3YBL24CA64V \
  | 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: d25ec6643cebf517cddbc057ae081ee56c76d74852cf320a3ecc0ef5ae6a91a4

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "05ade6be67c87e0afbc5def52126333fe90c0039e9d11a349f293546fa122a73",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV",
      "cs.MM"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-08T00:14:07Z",
    "title_canon_sha256": "4a7c2f2bf6b98b0011dcc95f1171af3a36e8b98077585534e5620b173448414d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.07061",
    "kind": "arxiv",
    "version": 2
  }
}