Pith Number

pith:E57JTNLK

pith:2026:E57JTNLKTRN4UJNBDMDDICPDVZ

not attested not anchored not stored refs resolved

CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth

Anuska Roy, Pravin Nair

CAB unifies flow and diffusion sampling by rectifying dynamics to one coordinate system then applying a corrected multistep predictor that needs no extra model calls.

arxiv:2605.16736 v1 · 2026-05-16 · 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{E57JTNLKTRN4UJNBDMDDICPDVZ}

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

The resulting method is simple, has the same algorithmic form across model classes, and has at least third-order local truncation error and second-order global error. Experiments on pretrained flow and diffusion models show that CAB improves quality-NFE trade-offs in the low-step regime of 6-20 NFEs.

C2weakest assumption

That the rectification step transforms the sampling dynamics of both flow and diffusion models into a common coordinate system where the multistep Adams-Bashforth predictor with correction term can be applied uniformly without introducing instability or order reduction.

C3one line summary

CAB accelerates flow and diffusion sampling via rectification to a shared coordinate system followed by a corrected Adams-Bashforth predictor that achieves third-order local truncation error while using no additional NFEs.

References

82 extracted · 82 resolved · 2 Pith anchors

[1] Denoising diffusion probabilistic models , author=. Proc. Advances in neural information processing systems , volume=

[2] Flow Matching for Generative Modeling , author=. Proc. International Conference on Learning Representations , year=

[3] Video Diffusion Models , author =. Proc. Advances in neural information processing systems , volume=

[4] IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=

[5] NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications , year = 2021

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:02:39.065073Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

277e99b56a9c5bca25a11b063409e3ae543f9f24e901c2141e4da52969289c36

Aliases

arxiv: 2605.16736 · arxiv_version: 2605.16736v1 · doi: 10.48550/arxiv.2605.16736 · pith_short_12: E57JTNLKTRN4 · pith_short_16: E57JTNLKTRN4UJNB · pith_short_8: E57JTNLK

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/E57JTNLKTRN4UJNBDMDDICPDVZ \
  | 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: 277e99b56a9c5bca25a11b063409e3ae543f9f24e901c2141e4da52969289c36

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9429f75217f0e1f02b867eafb02978cae37e8d6aa3f57e33dc6dde5c17069459",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T01:16:18Z",
    "title_canon_sha256": "cb00c5fed0056a7efb9a04f7377bcdee459016a714c41e6a7f4672c0ebc5b724"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16736",
    "kind": "arxiv",
    "version": 1
  }
}