Pith Number

pith:ROSGYSME

pith:2026:ROSGYSMEV4EN54I3REH6LNWMPY

not attested not anchored not stored refs resolved

Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation

Chang Xu, Jingxuan He, Mengyu Zheng, Xiyu Wang, Yunke Wang

Instruction-based image editing models show strong foreground-background separability in their earliest internal features, enabling zero-shot referring image segmentation from a single denoising step.

arxiv:2605.13122 v1 · 2026-05-13 · 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{ROSGYSMEV4EN54I3REH6LNWMPY}

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

strong foreground-background separability emerges in the internal representations of these models at the earliest denoising timestep, well before any visible image transformation occurs

C2weakest assumption

The feature-space separability observed at the earliest denoising timestep is sufficient to produce accurate pixel-level segmentation masks for arbitrary referring expressions without full synthesis or task-specific training.

C3one line summary

Pretrained instruction-based image editing models exhibit early foreground-background separability that enables a training-free framework for zero-shot referring image segmentation using a single denoising step.

References

54 extracted · 54 resolved · 8 Pith anchors

[1] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

[2] Instructpix2pix: Learning to follow image editing instructions 2023

[3] Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer 2025 · arXiv:2511.22699

[4] SAM 3: Segment Anything with Concepts 2025 · arXiv:2511.16719

[5] Dvin: Dynamic visual routing network for weakly supervised referring expression comprehension 2025

Receipt and verification

First computed	2026-05-18T03:08:57.947708Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8ba46c4984af08def11b890fe5b6cc7e350d92f1e553098186af0f177a134f38

Aliases

arxiv: 2605.13122 · arxiv_version: 2605.13122v1 · doi: 10.48550/arxiv.2605.13122 · pith_short_12: ROSGYSMEV4EN · pith_short_16: ROSGYSMEV4EN54I3 · pith_short_8: ROSGYSME

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/ROSGYSMEV4EN54I3REH6LNWMPY \
  | 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: 8ba46c4984af08def11b890fe5b6cc7e350d92f1e553098186af0f177a134f38

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "614f1fdbcde535dbabd02616efc86d5812e89a52ed3325aac570ea71a8af6888",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T07:48:05Z",
    "title_canon_sha256": "f72f8d5e2f63100ced3025e4845c319ec11eeb88ea3501a2329ba11189e7d739"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13122",
    "kind": "arxiv",
    "version": 1
  }
}