Pith Number

pith:YLPXIENM

pith:2026:YLPXIENMUS63UNDJCRGVGCY62D

not attested not anchored not stored refs pending

When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs

Hanzhe Hong, Heqing Du, Kaizhen Tan, Siru Tao, Yang Feng

Visual token pruning can lower calibration error in multimodal models while preserving accuracy.

arxiv:2604.12035 v2 · 2026-04-13 · 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{YLPXIENMUS63UNDJCRGVGCY62D}

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

On POPE, a pure-coverage setting in SCOPE achieves substantially lower ECE than the full unpruned model while maintaining similar accuracy. An internal alpha-sweep shows reducing the saliency weight improves calibration at all tested token budgets.

C2weakest assumption

That the specific datasets, model, token budgets, and pruning implementations tested are representative enough for the observed calibration trends to generalize beyond these conditions.

C3one line summary

Certain coverage-based visual token pruning strategies lower Expected Calibration Error compared to unpruned models while keeping accuracy similar on POPE, and pruning reduces ECE on ScienceQA-IMG.

Cited by

1 paper in Pith

Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference

Receipt and verification

First computed	2026-07-21T01:20:47.907710Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c2df7411aca4bdba3469144d530b1ed0d778380d0e80f1dbddc83d6d3a9d8f1c

Aliases

arxiv: 2604.12035 · arxiv_version: 2604.12035v2 · doi: 10.48550/arxiv.2604.12035 · pith_short_12: YLPXIENMUS63 · pith_short_16: YLPXIENMUS63UNDJ · pith_short_8: YLPXIENM

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/YLPXIENMUS63UNDJCRGVGCY62D \
  | 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: c2df7411aca4bdba3469144d530b1ed0d778380d0e80f1dbddc83d6d3a9d8f1c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dab49b90c0cb9521451afd006bc33abb77902fde9026f162d708046fe304f5bd",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-13T20:24:03Z",
    "title_canon_sha256": "087c9f3065710456573d1dde655622e449d3f2d4ff858c63ecaa6aea5c2c99e8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.12035",
    "kind": "arxiv",
    "version": 2
  }
}