Pith Number

pith:VHKEUZ3I

pith:2026:VHKEUZ3IXPWC47FBKG3Q5PAIQV

not attested not anchored not stored refs resolved

Sign Language Recognition in the Age of LLMs

Ivan Gruber, Jakub Honzik, Marek Hruz, Tomas Zelezny, Vaclav Javorek

Open-source VLMs lag far behind supervised classifiers in zero-shot sign language recognition but capture partial visual-semantic alignment.

arxiv:2604.11225 v1 · 2026-04-13 · cs.CV · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VHKEUZ3IXPWC47FBKG3Q5PAIQV}

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

under prompt-only zero-shot inference, current open-source VLMs remain far behind classic supervised ISLR classifiers by a wide margin. However, follow-up experiments reveal that these models capture partial visual-semantic alignment between signs and text descriptions. Larger proprietary models achieve substantially higher accuracy.

C2weakest assumption

That the chosen prompts, WLASL300 benchmark splits, and evaluation protocol provide an unbiased test of zero-shot capability without hidden advantages from prompt engineering or dataset characteristics.

C3one line summary

Zero-shot VLM evaluation on WLASL300 reveals open-source models lag far behind supervised ISLR baselines, but proprietary models improve with scale and exhibit some visual-semantic alignment.

References

44 extracted · 44 resolved · 2 Pith anchors

[1] Flamingo: a visual language model for few- shot learning 2022

[2] Pyav: Pythonic bindings for ffm- peg.https://github.com/PyAV-Org/PyAV

[3] Language models are few-shot learn- ers.Advances in neural information processing sys- tems, 33:1877–1901 1901

[4] Pillow (pil fork) documentation 2015

[5] Emerging Properties in Unified Multimodal Pretraining 2025 · arXiv:2505.14683

Receipt and verification

First computed	2026-06-26T01:15:51.643721Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a9d44a6768bbec2e7ca151b70ebc08857a337829f40148218e7a0a63763d2e35

Aliases

arxiv: 2604.11225 · arxiv_version: 2604.11225v1 · doi: 10.48550/arxiv.2604.11225 · pith_short_12: VHKEUZ3IXPWC · pith_short_16: VHKEUZ3IXPWC47FB · pith_short_8: VHKEUZ3I

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/VHKEUZ3IXPWC47FBKG3Q5PAIQV \
  | 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: a9d44a6768bbec2e7ca151b70ebc08857a337829f40148218e7a0a63763d2e35

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "44ced6aa60d597cb50792d3a19e7842afcfdf86471a96419bf6386deb79fbfd0",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-13T09:26:16Z",
    "title_canon_sha256": "5e0b1669158c91ef7efc2a3a42ac10d4b48af8a06f3d4bfab51d06a35b80f7ee"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.11225",
    "kind": "arxiv",
    "version": 1
  }
}