Pith Number

pith:UMFKTNZT

pith:2026:UMFKTNZTLFWUREPRT6TQXWSOZT

not attested not anchored not stored refs resolved

V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation

Aniruddha Mahapatra, Gedas Bertasius, Jonah Casebeer, Long Mai, Nicholas J. Bryan, Yan-Bo Lin

Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation.

arxiv:2603.11042 v2 · 2026-03-11 · cs.CV · cs.AI · cs.LG · cs.MM · cs.SD

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UMFKTNZTLFWUREPRT6TQXWSOZT}

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 results validate that temporal alignment through within-modality features is not only effective for video-to-music generation but also leads to better performance than paired cross-modal supervision.

C2weakest assumption

The assumption that event curves computed from intra-modal similarity using pretrained encoders provide comparable representations across modalities that enable direct substitution at inference without cross-modal training.

C3one line summary

V2M-Zero achieves state-of-the-art video-to-music generation with improved temporal synchronization and semantic alignment by substituting video event curves into a fine-tuned text-to-music model without any paired training data.

References

111 extracted · 111 resolved · 0 Pith anchors

[1] MusicLM: Generating music from text.arXiv Preprint, 2023 2023

[2] V-JEPA 2: Self-supervised video models enable understanding, prediction and planning.arXiv Preprint, 2025 2025

[3] Yatong Bai, Jonah Casebeer, Somayeh Sojoudi, and Nicholas J. Bryan. DRAGON: Distributional rewards optimize diffusion generative models.TMLR,

[4] AudioLM: a language modeling approach to audio generation 2023

[5] Re-bottleneck: Latent re-structuring for neural audio autoencoders 2025

Receipt and verification

First computed	2026-05-17T23:39:15.821418Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a30aa9b733596d4891f19fa70bda4ecce5224aa17e49642a73193ec5af8092b3

Aliases

arxiv: 2603.11042 · arxiv_version: 2603.11042v2 · doi: 10.48550/arxiv.2603.11042 · pith_short_12: UMFKTNZTLFWU · pith_short_16: UMFKTNZTLFWUREPR · pith_short_8: UMFKTNZT

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/UMFKTNZTLFWUREPRT6TQXWSOZT \
  | 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: a30aa9b733596d4891f19fa70bda4ecce5224aa17e49642a73193ec5af8092b3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2b4b7795a47e7fa658aaba5829c96d404691d5ce7cce175803fa0ef7b792c5ee",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG",
      "cs.MM",
      "cs.SD"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-03-11T17:59:40Z",
    "title_canon_sha256": "9ce94ec5dd521de0c93a5a80de2650e063ef221485df1654582f86cefdee8b29"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.11042",
    "kind": "arxiv",
    "version": 2
  }
}