Pith Number

pith:3JNQYK2S

pith:2026:3JNQYK2S4I7WI4PFLAQSS34ZUR

not attested not anchored not stored refs resolved

Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction

Jinjiang Guo

Classical ML models outperform larger pretrained and LLM approaches in most molecular prediction tasks for drug discovery

arxiv:2604.26498 v2 · 2026-04-29 · cs.LG · q-bio.QM

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{3JNQYK2S4I7WI4PFLAQSS34ZUR}

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

Across 156 fold mean comparisons, classical ML such as RF(ECFP4) and ExtraTrees(RDKit) win 116, GNNs such as GIN and Ligandformer win 25, pretrained sequence models such as MoLFormer and ChemBERTa2 win 12, and LLM based SAR baselines win three. Compact specialized models remain highly effective for molecular property and activity prediction.

C2weakest assumption

The 78 endpoint and split entries, grouped into ADME, toxicity and bioactivity classes and using random, Murcko scaffold, and structure-separated 5-fold CV, adequately represent the spectrum of real-world drug discovery challenges from closed-library retrospective evaluation to novel chemotype library expansion.

C3one line summary

A benchmark across 156 comparisons finds classical ML models win 116 times while larger pretrained and LLM models win far fewer, showing predictive performance depends on model-task fit rather than scale.

References

34 extracted · 34 resolved · 4 Pith anchors

[1] Feinberg, Evan and Gomes, Joseph and Geniesse, Caleb and S 2018 · doi:10.1039/c7sc02664a

[2] Coley, Cao Xiao, Jimeng Sun, and Marinka Zitnik 2021

[3] Bronskill, Krzysztof Maziarz, Henryk Misztela, Julien Lanini, Marwin Segler, Nadine Schneider, and Marc Brockschmidt 2021

[4] Limitations of representation learning in small molecule property prediction.Nature Communications, 14:6394, 2023 2023

[5] Jun Xia, Lecheng Zhang, Xiao Zhu, and Stan Z. Li. Why deep models often cannot beat non-deep counterparts on molecular property prediction?, 2023. URLhttps://arxiv.org/ abs/2306.17702 2023

Receipt and verification

First computed	2026-05-20T00:00:39.586358Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

da5b0c2b52e23f6471e55821296f99a46da4ca73fb416bcd32bdc54cec0ed4c3

Aliases

arxiv: 2604.26498 · arxiv_version: 2604.26498v2 · doi: 10.48550/arxiv.2604.26498 · pith_short_12: 3JNQYK2S4I7W · pith_short_16: 3JNQYK2S4I7WI4PF · pith_short_8: 3JNQYK2S

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/3JNQYK2S4I7WI4PFLAQSS34ZUR \
  | 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: da5b0c2b52e23f6471e55821296f99a46da4ca73fb416bcd32bdc54cec0ed4c3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "68f33d041722283f2502d820cb08e271088a761ed6bb332dd7e8585e5f5012a8",
    "cross_cats_sorted": [
      "q-bio.QM"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-29T10:01:16Z",
    "title_canon_sha256": "e9b2b6c7870d2c326f35efcd8a570b734b63e70cbab790c4ffccb8165d2683fb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.26498",
    "kind": "arxiv",
    "version": 2
  }
}