Pith Number

pith:WZ6RDVVJ

pith:2026:WZ6RDVVJEJG5TPMOVC6PW5RUQ7

not attested not anchored not stored refs resolved

Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering

Abhijeet Vishwasrao, Atharva Mahajan, Ricardo Vinuesa, Yuning Wang

A conditional flow matching model steers turbulent flow states to cut drag by 49 percent while using 37 times less energy than deep reinforcement learning.

arxiv:2605.14022 v1 · 2026-05-13 · physics.flu-dyn

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WZ6RDVVJEJG5TPMOVC6PW5RUQ7}

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

Policy-DRIFT achieves 49% drag reduction approaching the theoretical upper bound, which is ≈16% higher than the DRL benchmark, while consuming 37× less actuation energy.

C2weakest assumption

The conditional flow matching model constructs a physically-grounded manifold of realisable flow states that spans multiple control regimes without introducing unphysical artifacts or missing important dynamics.

C3one line summary

Policy-DRIFT combines conditional flow matching with terminal reward guidance and decoupled DRL to achieve 49% drag reduction in Re_tau=180 channel flow, 16% above DRL benchmarks and with 37 times less actuation energy.

References

12 extracted · 12 resolved · 4 Pith anchors

[1] M. Beneitez, A. Cremades, L. Guastoni, and R. Vinuesa. Improving turbulence control through explainable deep learning.arXiv preprint arXiv:2504.02354,

[2] Se (3)-stochastic flow matching for protein backbone generation

[3] H. Harder, A. Vishwasrao, L. Guastoni, R. Vinuesa, and S. Peitz. Efficient probabilistic surro- gate modeling techniques for partially-observed large-scale dynamical systems.arXiv preprint arXiv:2511.

[4] Planning with Diffusion for Flexible Behavior Synthesis · arXiv:2205.09991

[5] Continuous control with deep reinforcement learning · arXiv:1509.02971

Receipt and verification

First computed	2026-05-17T23:39:12.929164Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b67d11d6a9224dd9bd8ea8bcfb763487f7a897901f1ad2d680246dfd87b9af08

Aliases

arxiv: 2605.14022 · arxiv_version: 2605.14022v1 · doi: 10.48550/arxiv.2605.14022 · pith_short_12: WZ6RDVVJEJG5 · pith_short_16: WZ6RDVVJEJG5TPMO · pith_short_8: WZ6RDVVJ

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/WZ6RDVVJEJG5TPMOVC6PW5RUQ7 \
  | 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: b67d11d6a9224dd9bd8ea8bcfb763487f7a897901f1ad2d680246dfd87b9af08

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b1bdf1dfb0991d90fdb17b38a97f4b01a9e79a56740957508d96eba8d78317a3",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "physics.flu-dyn",
    "submitted_at": "2026-05-13T18:34:46Z",
    "title_canon_sha256": "4421a12d3198e5314db05bf08327707ee793b2663b238b2b657b4cb5b1d11d25"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14022",
    "kind": "arxiv",
    "version": 1
  }
}