Pith Number

pith:ZHXVBTKH

pith:2026:ZHXVBTKHPSFCHY4YHVUPKM3H65

not attested not anchored not stored refs resolved

TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion

Gedas Bertasius, Heather Yu, Marc Niethammer, Nurislam Tursynbek, Zhiqiang Lao

TeDiO improves temporal coherence in video diffusion by smoothing irregular diagonals in self-attention maps.

arxiv:2605.14136 v1 · 2026-05-13 · 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{ZHXVBTKHPSFCHY4YHVUPKM3H65}

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 multiple video diffusion models (e.g., Wan2.1, CogVideoX), TeDiO delivers markedly smoother motion while preserving per-frame visual quality.

C2weakest assumption

That irregular, fragmented temporal diagonals in self-attention maps are the primary cause of temporal incoherence and that lightweight latent updates to promote diagonal smoothness will reliably fix it without introducing new artifacts or degrading quality.

C3one line summary

TeDiO regularizes temporal diagonals in diffusion transformer attention maps to produce smoother video motion while keeping per-frame quality intact.

References

56 extracted · 56 resolved · 14 Pith anchors

[1] Prolific.https://www.prolific.com/. 7

[2] Cross-image attention for zero- shot appearance transfer 2024

[3] Uniedit: A unified tuning- free framework for video motion and appearance editing 2025

[4] Separate-and-enhance: Composi- tional finetuning for text-to-image diffusion models 2024

[5] Cd- tvd: Contrastive diffusion for 3d super-resolution with scarce high-resolution time-varying data.arXiv preprint arXiv:2508.08173, 2025 2025

Receipt and verification

First computed	2026-05-17T23:39:11.738810Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c9ef50cd477c8a23e3983d68f53367f77340812cd5cd1dae56ce399b4bda4b14

Aliases

arxiv: 2605.14136 · arxiv_version: 2605.14136v1 · doi: 10.48550/arxiv.2605.14136 · pith_short_12: ZHXVBTKHPSFC · pith_short_16: ZHXVBTKHPSFCHY4Y · pith_short_8: ZHXVBTKH

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/ZHXVBTKHPSFCHY4YHVUPKM3H65 \
  | 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: c9ef50cd477c8a23e3983d68f53367f77340812cd5cd1dae56ce399b4bda4b14

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7453587843dc047d4d68602196bb7bc5f8a38c218cb77f8b22f6c40537b0e7e6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T21:39:50Z",
    "title_canon_sha256": "2df332f88e4569fb9628aa4afdb41d113ad09be1c3d13ac421b83d85364364dd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14136",
    "kind": "arxiv",
    "version": 1
  }
}