pith:ZS5DTGOA
Learning Stable Predictors from Weak Supervision under Distribution Shift
Weak supervision under temporal shifts leads to negative R² in CRISPR perturbation models.
arxiv:2604.05002 v3 · 2026-04-05 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{ZS5DTGOAKVI2UO3OFOSAEYJ3YF}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
temporal transfer collapses across all model classes considered, yielding negative R² and weak or near-zero ρ (ridge R² = -0.145, ρ = 0.008; XGBoost R² = -0.155, ρ = 0.056; random forest R² = -0.322, ρ = 0.139)
that reusing a fixed weak-label construction across contexts successfully isolates supervision drift rather than introducing other unmeasured changes in the data-generating process
Weak supervision supports in-domain learning for CRISPR transcriptomic perturbations but temporal shifts cause negative R-squared and near-zero correlation across linear and tree models, unlike partial cell-line transfer.
Formal links
Receipt and verification
| First computed | 2026-05-20T02:05:42.968265Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
ccba3999c05551aa3b6e2ba402613bc16c751842a91967e26c05ef9d102dd6e5
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/ZS5DTGOAKVI2UO3OFOSAEYJ3YF \
| 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: ccba3999c05551aa3b6e2ba402613bc16c751842a91967e26c05ef9d102dd6e5
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "b3bc20a705016052e98644f5e6d371d5fff9b7f0d51aa785c73208b990b1c483",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-05T23:46:49Z",
"title_canon_sha256": "232c9a42bac7d400e0f8217fa6047044edd85eeca45bf05e69e5dc815cb4b910"
},
"schema_version": "1.0",
"source": {
"id": "2604.05002",
"kind": "arxiv",
"version": 3
}
}