Pith Number

pith:JVOVEPHL

pith:2026:JVOVEPHLNRHC3WTAD5GEUUDJH2

not attested not anchored not stored refs resolved

Dual-Pathway Circuits of Object Hallucination in Vision-Language Models

Aofan Liu, Ding Zhong, Guangyuan Dong, Jiaxin Liu, Pengcheng Fang, Qishi Zhan, Yue Wang, Zhaolu Kang, Zhidong Yang

Vision-language models contain a distinct hallucination pathway that can be suppressed to cut object errors by up to 76 percent with little accuracy loss.

arxiv:2605.13156 v1 · 2026-05-13 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JVOVEPHLNRHC3WTAD5GEUUDJH2}

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

targeted suppression of hallucination-pathway components, showing that scaling these components reduces object hallucination by up to 76% with minimal accuracy cost, and validate that the same circuit selectively transfers to relational but not attribute hallucination

C2weakest assumption

That activation patching and the observed polarity flip in grounding components causally identify and control hallucination behavior rather than reflecting correlated but non-causal patterns in model activations.

C3one line summary

Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.

References

42 extracted · 42 resolved · 14 Pith anchors

[1] Qwen3-VL Technical Report 2025 · arXiv:2511.21631

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

[3] Univg-r1: Reasoning guided universal visual grounding with reinforcement learning 2025

[4] A survey of multimodal hallucination evaluation and detection.International Journal of Computer Vision, 2025 2025

[5] Towards automated circuit discovery for mechanistic interpretability.Advances in Neural Information Processing Systems, 36, 2023 2023

Receipt and verification

First computed	2026-05-18T03:08:57.000692Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4d5d523ceb6c4e2dda601f4c4a50693e968c27ca5de481f06d55addca6602847

Aliases

arxiv: 2605.13156 · arxiv_version: 2605.13156v1 · doi: 10.48550/arxiv.2605.13156 · pith_short_12: JVOVEPHLNRHC · pith_short_16: JVOVEPHLNRHC3WTA · pith_short_8: JVOVEPHL

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/JVOVEPHLNRHC3WTAD5GEUUDJH2 \
  | 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: 4d5d523ceb6c4e2dda601f4c4a50693e968c27ca5de481f06d55addca6602847

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fb6634c051d1f47045c821ce868cb73fcd37c04fcc950a252aee8ec9a350994c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T08:20:01Z",
    "title_canon_sha256": "f89aa4ccbc871b468ff0db0c36bd2b0a0058586af4a5bf4f5f1227a05baba620"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13156",
    "kind": "arxiv",
    "version": 1
  }
}