Pith Number

pith:JS4M2AYZ

pith:2026:JS4M2AYZFPYABAXZZ3PRQG2ZP7

not attested not anchored not stored refs pending

Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models

Adriel Kuek, Hei Man Ip, Paul Pu Liang, Roy Ka-Wei Lee, Yuriel Ryan

Amplifying redundant multimodal interactions reduces visual errors in vision-language models by 38.3%.

arxiv:2605.08145 v2 · 2026-05-03 · cs.CV · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JS4M2AYZFPYABAXZZ3PRQG2ZP7}

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

Our findings suggest that increasing redundancy can reduce visual induced errors by 38.3% and improve consistency by 16.8%.

C2weakest assumption

The assumption that modern instruction datasets eliminate redundancies to prioritize visual grounding and that converting unique interactions to redundant ones via the Multimodal Interaction Gate will reliably compensate for impaired modalities without introducing new failure modes or losing synergistic information.

C3one line summary

A self-captioning method using a Multimodal Interaction Gate amplifies redundant interactions to reduce visual-induced errors by 38.3% and improve consistency by 16.8% in vision-language models.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-01T01:02:42.331369Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4cb8cd03192bf00082f9cedf181b597fcaa6223af31df2c0c0c4c3810ccdfeba

Aliases

arxiv: 2605.08145 · arxiv_version: 2605.08145v2 · doi: 10.48550/arxiv.2605.08145 · pith_short_12: JS4M2AYZFPYA · pith_short_16: JS4M2AYZFPYABAXZ · pith_short_8: JS4M2AYZ

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/JS4M2AYZFPYABAXZZ3PRQG2ZP7 \
  | 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: 4cb8cd03192bf00082f9cedf181b597fcaa6223af31df2c0c0c4c3810ccdfeba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6118f9d36a2f38f7e4a8bb8c5466d318ef0dda186be38020f447e17d7d5fe4ee",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-03T06:25:45Z",
    "title_canon_sha256": "df4ffbc0418d9e796aa3ec3316389184bfe68c5ec5024de7d1ffb96cc6f2e5d6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.08145",
    "kind": "arxiv",
    "version": 2
  }
}