Pith Number

pith:GCKRMTXF

pith:2026:GCKRMTXFY54TIY236BBCHRC5KA

not attested not anchored not stored refs pending

Mean Flow Policy Optimization

Jian Cheng, Xiaoyi Dong, Xi Sheryl Zhang

Mean Flow Policy Optimization uses few-step flow models to represent RL policies, matching diffusion performance while cutting training and inference time.

arxiv:2604.14698 v2 · 2026-04-16 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GCKRMTXFY54TIY236BBCHRC5KA}

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

Experiments on MuJoCo and DeepMind Control Suite benchmarks demonstrate that our method, Mean Flow Policy Optimization (MFPO), achieves performance comparable to or exceeding current diffusion-based baselines while considerably reducing training and inference time.

C2weakest assumption

That the two MeanFlow-specific challenges (action likelihood evaluation and soft policy improvement) can be solved without introducing new instabilities or bias that would undermine the maximum-entropy guarantees.

C3one line summary

Mean Flow Policy Optimization (MFPO) uses few-step flow-based models for RL policies and achieves performance on par with or better than diffusion-based methods while substantially lowering training and inference time on MuJoCo and DeepMind Control Suite.

Receipt and verification

First computed	2026-06-02T01:03:47.086410Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3095164ee5c77934635bf04223c45d501ce57a3bb5430e0d8a08d69180339aa1

Aliases

arxiv: 2604.14698 · arxiv_version: 2604.14698v2 · doi: 10.48550/arxiv.2604.14698 · pith_short_12: GCKRMTXFY54T · pith_short_16: GCKRMTXFY54TIY23 · pith_short_8: GCKRMTXF

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/GCKRMTXFY54TIY236BBCHRC5KA \
  | 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: 3095164ee5c77934635bf04223c45d501ce57a3bb5430e0d8a08d69180339aa1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "273f9a2f9c9f6f7f09bbec71c9a85917d5d5065692d31d9c7a210cf5f24d6422",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-16T06:59:52Z",
    "title_canon_sha256": "f27c14e1194659c707d299ba216b954da90bbdfca46497d6700c04e4ab8e144b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.14698",
    "kind": "arxiv",
    "version": 2
  }
}