Pith Number

pith:KZDIAXPC

pith:2026:KZDIAXPC6XUZ3LMYIRLIYYQMLS

not attested not anchored not stored refs resolved

MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation

Damiano Bertolini, Daniel Cremers, Dong Wang, Niclas Zeller, Qing Cheng, Wei Zhang

MambaPanoptic replaces transformers and convolutions with structured state space blocks to achieve competitive panoptic segmentation at linear complexity.

arxiv:2605.12640 v1 · 2026-05-12 · 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{KZDIAXPC6XUZ3LMYIRLIYYQMLS}

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 the Cityscapes and COCO panoptic segmentation benchmarks demonstrate that MambaPanoptic consistently outperforms PanopticDeepLab and PanopticFCN under comparable model sizes, and matches or surpasses Mask2Former on Cityscapes in PQ and AP while requiring fewer parameters.

C2weakest assumption

That Mamba blocks can be directly substituted into a PanopticFCN-style kernel generator and top-down FPN while preserving the necessary multi-scale coherence and boundary accuracy for both thing and stuff classes without additional task-specific adaptations.

C3one line summary

MambaPanoptic replaces CNN and transformer components with Mamba blocks in a feature pyramid and kernel generator, achieving higher panoptic quality than PanopticDeepLab and PanopticFCN on Cityscapes and COCO while using fewer parameters than Mask2Former.

References

39 extracted · 39 resolved · 3 Pith anchors

[1] End-to-end object detection with transformers 2020

[2] D., Zhu, Y., Liu, T., Huang, T 2020

[3] G., Kirillov, A., Girdhar, R., 2022 2022

[4] Per-pixel classification is not all you need for semantic segmentation 2021

[5] The cityscapes dataset for semantic urban scene understanding 2016

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:10:00.012201Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce

Aliases

arxiv: 2605.12640 · arxiv_version: 2605.12640v1 · doi: 10.48550/arxiv.2605.12640 · pith_short_12: KZDIAXPC6XUZ · pith_short_16: KZDIAXPC6XUZ3LMY · pith_short_8: KZDIAXPC

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/KZDIAXPC6XUZ3LMYIRLIYYQMLS \
  | 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: 5646805de2f5e99dad9844568c620c5ca9ff0d85c085df02d034968796f0afce

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6d448bbcd8cbe23b6da141dd86d19f54b93eaf500b0afa95eb722f6cbb47b89e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-12T18:30:49Z",
    "title_canon_sha256": "bc0e8492167e38dae6d27e8cf108daf4447ce5315cd1ed06e0bb8092964590a4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12640",
    "kind": "arxiv",
    "version": 1
  }
}