Pith Number
pith:43XJWIZM
pith:2026:43XJWIZMTQALRDFTVUWDKTD73L
not attested
not anchored
not stored
refs resolved
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase.
arxiv:2605.13724 v1 · 2026-05-13 · cs.CV · cs.AI
Record completeness
1
Bitcoin timestamp
2
Internet Archive
3
Author claim
· sign in to
claim
4
Citations
5
Replications
✓
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
AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime, while scaling with sampling step budgets.
C2weakest assumption
That learning flow-map transitions over arbitrary intervals via backward simulation will avoid introducing new discretization or exposure biases that undermine the original ODE scaling behavior.
C3one line summary
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
References
[1] Wan: Open and Advanced Large-Scale Video Generative Models
[2] Cosmos World Foundation Model Platform for Physical AI
[3] HunyuanVideo: A Systematic Framework For Large Video Generative Models
[4] CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
[5] LTX-Video: Realtime Video Latent Diffusion
Formal links
Receipt and verification
| First computed | 2026-05-18T02:44:16.626721Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/43XJWIZMTQALRDFTVUWDKTD73L \
| 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: e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "0d17f10040eef6d0c79d044c96895c686b2383ca26c9d6d5a87778a88fc26ad6",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-13T16:06:34Z",
"title_canon_sha256": "53af612fb312196dd64b2d9c814636fb81cf9acc283cd82a90f27d488622547e"
},
"schema_version": "1.0",
"source": {
"id": "2605.13724",
"kind": "arxiv",
"version": 1
}
}