pith:GAHNLIGV
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
Evidence for cross-modal neural network convergence weakens at large scales and realistic conditions
arxiv:2604.18572 v2 · 2026-04-20 · cs.CV · cs.AI · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{GAHNLIGVIFTDCMYQADPA2DH3JB}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We show that the experimental evidence for this hypothesis is fragile and depends critically on the evaluation regime. Alignment ... degrades substantially as the dataset is scaled to millions of samples.
That mutual nearest-neighbor overlap measured on large-scale, many-to-many image-text pairs is a faithful indicator of whether fine-grained representational structure has converged.
Evidence for cross-modal representational convergence weakens substantially at scale and in realistic many-to-many settings, indicating models learn rich but distinct representations.
Receipt and verification
| First computed | 2026-06-03T02:05:47.682345Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
300ed5a0d5416631331000de0d0cfb485bb9405e682b1017d15d23ec3ecbae17
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/GAHNLIGVIFTDCMYQADPA2DH3JB \
| 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: 300ed5a0d5416631331000de0d0cfb485bb9405e682b1017d15d23ec3ecbae17
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "49517b19e26333b740c725f548c87bb36956011c9e171df64a3fdffde2c2c4d4",
"cross_cats_sorted": [
"cs.AI",
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-20T17:56:02Z",
"title_canon_sha256": "3ebd6dc6108b88b305009f20a03871a9b8c17084fbd8c3c227c1791bedcb2407"
},
"schema_version": "1.0",
"source": {
"id": "2604.18572",
"kind": "arxiv",
"version": 2
}
}