Pith Number

pith:IJWCJCPD

pith:2026:IJWCJCPDBTFID3NV3NGM7HQTGW

not attested not anchored not stored refs resolved

PaMM: Periodic Motif Memory for Atomistic Models with an Explicit Local-Structure Interface

Ryan Dong

Explicit pair and triplet motif lookup tables improve energy and force accuracy in periodic atomistic models at intermediate training steps.

arxiv:2605.13297 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{IJWCJCPDBTFID3NV3NGM7HQTGW}

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

in the studied UMA-S + OMAT regime, explicit pair/triplet motif memory is a useful inductive bias for periodic atomistic modeling.

C2weakest assumption

That the observed gains at the 10k- and 20k-step checkpoints are driven by the structured motif organization rather than incidental capacity or optimization effects, and that the same pattern would persist at full convergence or on other datasets.

C3one line summary

PaMM augments an equivariant atomistic model with explicit pair and triplet motif memory tables, producing modest gains in energy and force MAE on OMAT benchmarks at fixed training budget.

References

10 extracted · 10 resolved · 0 Pith anchors

[1] UMA: A Family of Universal Models for Atoms , author=. 2025 , eprint= 2025

[2] Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models , author=. 2026 , eprint= 2026

[3] Nature Communications , volume=

[4] MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields , author=. 2022 , eprint= 2022

[5] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations , author=. 2023 , eprint= 2023

Receipt and verification

First computed	2026-05-18T02:44:49.072971Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

426c2489e30cca81edb5db4ccf9e13358f1eda4575934fee9a4db9059e2d1c81

Aliases

arxiv: 2605.13297 · arxiv_version: 2605.13297v1 · doi: 10.48550/arxiv.2605.13297 · pith_short_12: IJWCJCPDBTFI · pith_short_16: IJWCJCPDBTFID3NV · pith_short_8: IJWCJCPD

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/IJWCJCPDBTFID3NV3NGM7HQTGW \
  | 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: 426c2489e30cca81edb5db4ccf9e13358f1eda4575934fee9a4db9059e2d1c81

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2de67347fa5fd51b8be8bfac5f2a76a7e541a297e5d5d5e79ed6546ee20d3bbe",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T10:11:27Z",
    "title_canon_sha256": "e83ac2c615c2dc95206747807d9fe50a3ddf0775872fd6f7a5913ad4438cca4a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13297",
    "kind": "arxiv",
    "version": 1
  }
}