Pith Number

pith:6XAIUR2G

pith:2026:6XAIUR2GYONFPTZCI4R7XQDBSB

not attested not anchored not stored refs resolved

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL

Minshuo Chen, Philip Torr, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Sipeng Chen, Yijiang Li, Zhaoran Wang, Zhenfei Yin, Zhenyang Ni

CreFlow uses automatically generated Linear Temporal Logic rewards plus corrective reflow to align video diffusion rollouts with embodied task rules and lift downstream success 23.8 points.

arxiv:2605.14274 v1 · 2026-05-14 · 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{6XAIUR2GYONFPTZCI4R7XQDBSB}

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

CreFlow yields reward judgments better aligned with human and simulator success labels than existing methods and improves downstream execution success by 23.8 percentage points across eight bimanual manipulation tasks.

C2weakest assumption

That the automatically formulated LTL constraints provide faithful, localized rewards without significant manual engineering or domain-specific tuning, and that the corrective reflow loss reliably stabilizes high-dimensional video diffusion updates in practice.

C3one line summary

CreFlow combines LTL compositional rewards with credit-aware NFT and corrective reflow losses in online RL to improve embodied video diffusion models, raising downstream task success by 23.8 percentage points on eight bimanual manipulation tasks.

References

45 extracted · 45 resolved · 22 Pith anchors

[1] Cosmos World Foundation Model Platform for Physical AI 2025 · arXiv:2501.03575

[2] Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation 2024 · arXiv:2409.16283

[3] Motus: A Unified Latent Action World Model 2025 · arXiv:2512.13030

[4] $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization 2025 · arXiv:2504.16054

[5] SAM 3: Segment Anything with Concepts 2025 · arXiv:2511.16719

Receipt and verification

First computed	2026-05-17T23:39:10.362385Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f5c08a4746c39a57cf224723fbc061904754c270534347d31de2c1010049c53d

Aliases

arxiv: 2605.14274 · arxiv_version: 2605.14274v1 · doi: 10.48550/arxiv.2605.14274 · pith_short_12: 6XAIUR2GYONF · pith_short_16: 6XAIUR2GYONFPTZC · pith_short_8: 6XAIUR2G

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/6XAIUR2GYONFPTZCI4R7XQDBSB \
  | 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: f5c08a4746c39a57cf224723fbc061904754c270534347d31de2c1010049c53d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "37ec7e054359b823a87cddfe110a26171fcb72f316bcafd8535a8a9165226c43",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T02:18:58Z",
    "title_canon_sha256": "1b215cebce7d0e38ab236f9d44487c275a2e490f5694c52f84d4a62268eba5b7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14274",
    "kind": "arxiv",
    "version": 1
  }
}