pith. sign in
Pith Number

pith:M6T2WLTQ

pith:2026:M6T2WLTQJO6K4LA6SP3IBXMGUC
not attested not anchored not stored refs pending

EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors

Kei Harada, Ryuhei Miyazato, Shunsuke Kitada

EnsemHalDet improves hallucination detection in vision-language models by ensembling detectors from multiple internal states.

arxiv:2604.02784 v2 · 2026-04-03 · cs.CV · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{M6T2WLTQJO6K4LA6SP3IBXMGUC}

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

EnsemHalDet consistently outperforms prior methods and single-detector models in terms of AUC across multiple VQA datasets and VLMs.

C2weakest assumption

That the chosen internal representations (attention outputs and hidden states) supply sufficiently diverse and complementary hallucination signals that can be combined effectively by ensemble learning.

C3one line summary

EnsemHalDet improves hallucination detection in VLMs by ensembling independent detectors on diverse internal states, yielding higher AUC than single-detector baselines on VQA datasets.

Receipt and verification
First computed 2026-05-20T01:05:12.453408Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

67a7ab2e704bbcae2c1e93f680dd86a09558056bd61b5ddb2dc381396fca99b3

Aliases

arxiv: 2604.02784 · arxiv_version: 2604.02784v2 · doi: 10.48550/arxiv.2604.02784 · pith_short_12: M6T2WLTQJO6K · pith_short_16: M6T2WLTQJO6K4LA6 · pith_short_8: M6T2WLTQ
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/M6T2WLTQJO6K4LA6SP3IBXMGUC \
  | 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: 67a7ab2e704bbcae2c1e93f680dd86a09558056bd61b5ddb2dc381396fca99b3
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "738c55bb07479d179d1811524fbd914f228950bf16dadee89e4261c309996b93",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-03T06:48:27Z",
    "title_canon_sha256": "699cb3718481908c167998b5c43a73505704b40e97d434ac6fc3880162b41adf"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.02784",
    "kind": "arxiv",
    "version": 2
  }
}