Pith Number

pith:XJXDZDJI

pith:2026:XJXDZDJIMCDXDCGGBCICCL6MRN

not attested not anchored not stored refs resolved

WOW-Seg: A Word-free Open World Segmentation Model

Bin Li, Danyang Li, Ming-Ming Cheng, Tianhao Wu, Xiang Li, Yang Zhang, Yuxuan Li, Zhenyuan Chen

A word-free model segments and recognizes open-world objects by aligning visual masks directly to vision-language features.

arxiv:2605.16903 v1 · 2026-05-16 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XJXDZDJIMCDXDCGGBCICCL6MRN}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

WOW-Seg attains strong results on the LVIS dataset, achieving a semantic similarity of 89.7 and a semantic IoU of 82.4. This performance surpasses the previous SOTA while using only one-eighth the parameter count.

C2weakest assumption

The Mask2Token module successfully aligns visual mask tokens with the VLLM feature space in a way that supports open-set recognition without any text supervision or category-specific training data.

C3one line summary

WOW-Seg proposes a word-free open-world segmentation model using Mask2Token and Cascade Attention Mask modules, reporting 89.7 semantic similarity and 82.4 semantic IoU on LVIS with one-eighth the parameters of prior SOTA plus a new 7,662-class benchmark.

References

32 extracted · 32 resolved · 12 Pith anchors

[1] Qwen2.5-VL Technical Report · arXiv:2502.13923

[2] Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic · arXiv:2306.15195

[3] Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling · arXiv:2412.05271

[4] Imagenet: A large-scale hi- erarchical image database 2026

[5] Tag: Guidance-free open-vocabulary semantic segmenta- tion.arXiv preprint arXiv:2403.11197,

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:29.320227Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ba6e3c8d2860877188c60890212fcc8b4e61374b1fc8caa39ba16ed65681c526

Aliases

arxiv: 2605.16903 · arxiv_version: 2605.16903v1 · doi: 10.48550/arxiv.2605.16903 · pith_short_12: XJXDZDJIMCDX · pith_short_16: XJXDZDJIMCDXDCGG · pith_short_8: XJXDZDJI

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/XJXDZDJIMCDXDCGGBCICCL6MRN \
  | 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: ba6e3c8d2860877188c60890212fcc8b4e61374b1fc8caa39ba16ed65681c526

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9de3ce4401b6ea8db64491f6687e85c7bc99cf9973d46c58cf02214ca9fdc1dc",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T09:28:46Z",
    "title_canon_sha256": "c8d205046de8d48040a3f1624b4e2005008cc3a1fbd429f0f8c489012a69e057"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16903",
    "kind": "arxiv",
    "version": 1
  }
}