Pith Number

pith:E2J37SDC

pith:2026:E2J37SDCCMVIRZUBTAH7WUZECI

not attested not anchored not stored refs resolved

GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations

Chengchang Pan, Honggang Qi, Zesheng Li

A learned prefix transform reorganizes frozen vision-language embeddings so that length directly controls semantic granularity from coarse to fine.

arxiv:2605.17727 v1 · 2026-05-18 · 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{E2J37SDCCMVIRZUBTAH7WUZECI}

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

frozen VLM embeddings can be reorganized into a truncatable semantic prefix interface rather than merely compressed

C2weakest assumption

A single shared near-orthogonal prefix transform learned over frozen embeddings can progressively assign coarse-to-fine semantic roles to increasing prefix lengths while preserving full-dimensional geometry (stated in the abstract description of the Semantic Matryoshka interface).

C3one line summary

GraSP-VL turns frozen VLM embedding length into a controllable semantic granularity interface via a learned shared prefix transform that creates a Semantic Matryoshka structure.

References

46 extracted · 46 resolved · 0 Pith anchors

[1] Proceedings of the 38th International Conference on Machine Learning , pages = 2021

[2] Proceedings of the 38th International Conference on Machine Learning , pages = 2021

[3] Lawrence Zitnick 2014 · doi:10.1007/978-3-319-10602-1_48

[4] Transactions of the Association for Computational Linguistics , volume = 2014

[5] 2022 , url = 2022

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:55.065340Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2693bfc862132a88e681980ffb53241210e67a137bb13c244e873c9ab6f36dad

Aliases

arxiv: 2605.17727 · arxiv_version: 2605.17727v1 · doi: 10.48550/arxiv.2605.17727 · pith_short_12: E2J37SDCCMVI · pith_short_16: E2J37SDCCMVIRZUB · pith_short_8: E2J37SDC

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/E2J37SDCCMVIRZUBTAH7WUZECI \
  | 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: 2693bfc862132a88e681980ffb53241210e67a137bb13c244e873c9ab6f36dad

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "512cb5f6694633042dc6218630d237d91f3acfd69ca9966fe53f7406b5eadec8",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-18T01:10:07Z",
    "title_canon_sha256": "488d42dad8b4ec8da4d4f691627f3204062d07abcf4e5d51fcd172f618baadc1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17727",
    "kind": "arxiv",
    "version": 1
  }
}