Pith Number

pith:J2YFXZY3

pith:2026:J2YFXZY33UMKM3KW4LC76TAFPL

not attested not anchored not stored refs pending

Motif-Video 2B: Technical Report

Beomgyu Kim, Bokki Ryu, Changjin Kang, Dahye Choi, Dongjoo Weon, Dongpin Oh, Dongseok Kim, Eunhwan Park, Haesol Lee, Hanbin Jung, Hongjoo Lee, Hyeyeon Cho, Hyukjin Kweon, Jaeheui Her, Jaeyeon Huh, Jangwoong Kim, Jeesoo Lee, Jeongdoo Lee, Junghwan Lim, Junhyeok Lee, Minjae Kim, Minsu Ha, Sungmin Lee, Taehyun Kim, Taewhan Kim, Wai Ting Cheung, Yeongjae Park, Youngrok Kim

Separating prompt alignment, temporal consistency, and fine-detail recovery into distinct stages lets a 2B video model outperform a 14B baseline on VBench with far less data and compute.

arxiv:2604.16503 v2 · 2026-04-14 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{J2YFXZY33UMKM3KW4LC76TAFPL}

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

On VBench, Motif-Video~2B reaches 83.76%, surpassing Wan2.1 14B while using 7× fewer parameters and substantially less training data.

C2weakest assumption

That separating prompt alignment, temporal consistency, and fine-detail recovery into distinct architectural stages actually reduces interference and drives the observed gains, rather than the gains arising mainly from the dynamic token routing, early feature alignment, or other unstated aspects of the training recipe.

C3one line summary

Motif-Video 2B achieves 83.76% VBench score, beating a 14B-parameter baseline with 7x fewer parameters and substantially less training data through shared cross-attention and a three-part backbone.

Receipt and verification

First computed	2026-05-20T01:05:13.743500Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4eb05be71bdd18a66d56e2c5ff4c057ae5d5ebce652b2fd009f2812f8bdce389

Aliases

arxiv: 2604.16503 · arxiv_version: 2604.16503v2 · doi: 10.48550/arxiv.2604.16503 · pith_short_12: J2YFXZY33UMK · pith_short_16: J2YFXZY33UMKM3KW · pith_short_8: J2YFXZY3

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/J2YFXZY33UMKM3KW4LC76TAFPL \
  | 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: 4eb05be71bdd18a66d56e2c5ff4c057ae5d5ebce652b2fd009f2812f8bdce389

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "69298a6784daed110a9554e6e6b78272b8737d3308231f726b583112a9e3d994",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-14T15:09:39Z",
    "title_canon_sha256": "6e8b79a904223c58498d3f57c7a29bfacc6c6429f415b10f39c0be4dac8db7b7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.16503",
    "kind": "arxiv",
    "version": 2
  }
}