pith:SYENSNTG
Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization
SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search.
arxiv:2604.08324 v3 · 2026-04-09 · cs.NE · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{SYENSNTG2SJZO5TJAC3IIFQTZ4}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our experiments show that: (1) cross-modal alignment does not improve during optimization, even as fitness increases, and (2) the alignment learned by SNIP is too coarse to efficiently conduct principled search in the symbolic space.
The assumption that the chosen metrics for cross-modal alignment and the optimization process accurately capture whether the alignment enables effective bi-modal search, without confounding factors from the specific experimental setup or choice of SNIP hyperparameters.
Experiments reveal that cross-modal alignment in SNIP does not improve with increasing fitness and is too coarse for effective symbolic search in latent space optimization for symbolic regression.
Receipt and verification
| First computed | 2026-06-02T02:04:17.239321Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4 \
| 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: 9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "5403a71c759e81aa0543492264ba46c90be7a2eba9751d257b99a089eab6d560",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.NE",
"submitted_at": "2026-04-09T14:55:36Z",
"title_canon_sha256": "3c9ebf048320b667acb632d18395369f479a7eaa5c856ec005ba4cd395d5543d"
},
"schema_version": "1.0",
"source": {
"id": "2604.08324",
"kind": "arxiv",
"version": 3
}
}