Pith Number

pith:FHFH2UCH

pith:2026:FHFH2UCHJ7D22IKMFDNGRPQF5X

not attested not anchored not stored refs resolved

Tensor Channel Equivariant Graph Neural Networks for Molecular Polarizability Prediction

Daniel Franzen, Jean Philip Filling, Michael Wand

Propagating explicit tensor channels through message passing improves molecular polarizability tensor predictions over readout-only baselines.

arxiv:2605.16891 v1 · 2026-05-16 · 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{FHFH2UCHJ7D22IKMFDNGRPQF5X}

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

On optimized QM7-X geometries the proposed model achieves lower full-tensor and anisotropic error than both a PaiNN-style readout baseline and a dielectric MACE baseline under matched training conditions and at nearly identical parameter count.

C2weakest assumption

The performance gain is attributable to explicit tensor propagation and traceless target parameterization rather than to differences in optimization dynamics or data preprocessing that were not fully controlled in the reported experiments (abstract, paragraph on ablation studies).

C3one line summary

A tensor-channel equivariant GNN based on PaiNN propagates symmetric rank-2 tensor features during message passing and achieves lower full-tensor and anisotropic error than readout-only and MACE baselines on QM7-X geometries.

References

21 extracted · 21 resolved · 2 Pith anchors

[1] Mace-polar-1: A polarisable electrostatic foun- dation model for molecular chemistry 2026

[2] Advances in neural information processing systems35, 11423–11436 (2022) 2022

[3] Nature communications13(1), 2453 (2022) 2022

[4] 04615 12 Filling et al 2019

[5] S., & Welling, M., 2016,Group Equivariant Convolu- tional Networks, Proc 2016 · arXiv:1602.07576

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:28.607752Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

29ca7d50474fc7ad214c28da68be05ede8f9b5e08e41c339b58a1d7ad21dc05c

Aliases

arxiv: 2605.16891 · arxiv_version: 2605.16891v1 · doi: 10.48550/arxiv.2605.16891 · pith_short_12: FHFH2UCHJ7D2 · pith_short_16: FHFH2UCHJ7D22IKM · pith_short_8: FHFH2UCH

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/FHFH2UCHJ7D22IKMFDNGRPQF5X \
  | 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: 29ca7d50474fc7ad214c28da68be05ede8f9b5e08e41c339b58a1d7ad21dc05c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b7839616559cfa19d6965321fe6bf2d467152a7e849f112a25f0fee464b438e8",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T09:07:07Z",
    "title_canon_sha256": "0804edd11bd02e1fd4626e7a2cd9c4d545f7fc4531dcef1bc7e180e1256dc870"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16891",
    "kind": "arxiv",
    "version": 1
  }
}