Pith Number

pith:WDOZ2HEG

pith:2026:WDOZ2HEGX4VBAXQZBTLGS6INI2

not attested not anchored not stored refs resolved

Rethinking Molecular OOD Generalization via Target-Aware Source Selection

Duanhua Cao, Jiajun Yu, Jiameng Chen, Kun Li, Wenbin Hu, Yizhen Zheng, Zhuohao Lin

A reinforcement learning policy selects source subsets to reduce extreme out-of-distribution errors in molecular property prediction by up to 11 percent.

arxiv:2605.13932 v1 · 2026-05-13 · 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{WDOZ2HEGX4VBAXQZBTLGS6INI2}

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

Evaluations show that prediction errors of state-of-the-art 3D molecular models surge by up to 8.0x on SCOPE-BENCH with a mean of 5.9x, while POMA achieves up to an 11.2% reduction in mean absolute error with an average relative improvement of 6.2% across diverse backbone architectures.

C2weakest assumption

The reinforcement-learning policy can reliably identify source subsets that avoid negative transfer under extreme structural shifts, and that cluster-level partitioning in physicochemical descriptor space fully eliminates microscopic semantic overlap between source and target.

C3one line summary

SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.

References

58 extracted · 58 resolved · 5 Pith anchors

[1] Invariant Risk Minimization 1907 · arXiv:1907.02893

[2] k-means++: The advantages of careful seeding 2007

[3] Gotennet: Rethinking efficient 3d equivariant graph neural networks 2025

[4] Why is tanimoto index an appropriate choice for fingerprint-based similarity calculations?Journal of cheminformatics, 7(1):20 2015

[5] E (n) equivariant topological neural networks.arXiv preprint arXiv:2405.15429, 2024 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:13.968678Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b0dd9d1c86bf2a105e190cd669790d46acbf41d21fe9fa714095b07f270397aa

Aliases

arxiv: 2605.13932 · arxiv_version: 2605.13932v1 · doi: 10.48550/arxiv.2605.13932 · pith_short_12: WDOZ2HEGX4VB · pith_short_16: WDOZ2HEGX4VBAXQZ · pith_short_8: WDOZ2HEG

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/WDOZ2HEGX4VBAXQZBTLGS6INI2 \
  | 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: b0dd9d1c86bf2a105e190cd669790d46acbf41d21fe9fa714095b07f270397aa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1fcc1b6eb392bc6c0eef1b0d33d4ee7ab22b61133ac819d1bdce871498a63bac",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T16:09:46Z",
    "title_canon_sha256": "1125032e586b2f70d0a725044071fdb43bf5b1b24c1e4be8eca8bdedf2241081"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13932",
    "kind": "arxiv",
    "version": 1
  }
}