{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BDSWREBYIVAUPTLEPE4AKH7LYA","short_pith_number":"pith:BDSWREBY","schema_version":"1.0","canonical_sha256":"08e5689038454147cd647938051febc0280830b8362d7bc80cb9e0ea372a0885","source":{"kind":"arxiv","id":"2504.16068","version":1},"attestation_state":"computed","paper":{"title":"High-performance training and inference for deep equivariant interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"physics.comp-ph","authors_text":"Aadit Saluja, Albert Musaelian, Anders Johansson, Boris Kozinsky, Chuin Wei Tan, Gabriel de Miranda Nascimento, Laura Zichi, Marc L. Descoteaux, Menghang Wang, Mit Kotak, Se\\'an R. Kavanagh, Tess Smidt, William C. Witt, Yizhong R. Hu","submitted_at":"2025-04-22T17:47:01Z","abstract_excerpt":"Machine learning interatomic potentials, particularly those based on deep equivariant neural networks, have demonstrated state-of-the-art accuracy and computational efficiency in atomistic modeling tasks like molecular dynamics and high-throughput screening. The size of datasets and demands of downstream workflows are growing rapidly, making robust and scalable software essential. This work presents a major overhaul of the NequIP framework focusing on multi-node parallelism, computational performance, and extensibility. The redesigned framework supports distributed training on large datasets a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.16068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2025-04-22T17:47:01Z","cross_cats_sorted":["cs.LG","physics.chem-ph"],"title_canon_sha256":"548e36b6fcdf97fe2bec5d38e7e95da0cc8df5551550bf672047129c5eee5479","abstract_canon_sha256":"caa1bdbef61bb869f3566c03c50cf472ef5259eff5f545edcc55574934864076"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:34.960672Z","signature_b64":"IQtUxjrXhHLIY+EwWKePB8uQZQjmKxtoBRO4jVw9aTpfN9wPgZ3ONkrIRraRgCpzj4ksI0zqtmu34HRoz0wrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08e5689038454147cd647938051febc0280830b8362d7bc80cb9e0ea372a0885","last_reissued_at":"2026-07-05T10:52:34.960196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:34.960196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-performance training and inference for deep equivariant interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"physics.comp-ph","authors_text":"Aadit Saluja, Albert Musaelian, Anders Johansson, Boris Kozinsky, Chuin Wei Tan, Gabriel de Miranda Nascimento, Laura Zichi, Marc L. Descoteaux, Menghang Wang, Mit Kotak, Se\\'an R. Kavanagh, Tess Smidt, William C. Witt, Yizhong R. Hu","submitted_at":"2025-04-22T17:47:01Z","abstract_excerpt":"Machine learning interatomic potentials, particularly those based on deep equivariant neural networks, have demonstrated state-of-the-art accuracy and computational efficiency in atomistic modeling tasks like molecular dynamics and high-throughput screening. The size of datasets and demands of downstream workflows are growing rapidly, making robust and scalable software essential. This work presents a major overhaul of the NequIP framework focusing on multi-node parallelism, computational performance, and extensibility. The redesigned framework supports distributed training on large datasets a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16068","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.16068/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.16068","created_at":"2026-07-05T10:52:34.960258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16068v1","created_at":"2026-07-05T10:52:34.960258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16068","created_at":"2026-07-05T10:52:34.960258+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDSWREBYIVAU","created_at":"2026-07-05T10:52:34.960258+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDSWREBYIVAUPTLE","created_at":"2026-07-05T10:52:34.960258+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDSWREBY","created_at":"2026-07-05T10:52:34.960258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18691","citing_title":"Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":240,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25351","citing_title":"Anomalous Subsurface Vacancy Stabilization Dictated by Geometry-Electronic Decoupling on Metal Surfaces","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30822","citing_title":"Using graph neural networks to predict many-body interactions in amorphous materials","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2512.25061","citing_title":"Physics-Constrained Self-Energy Warm Starts for Charge-Self-Consistent DFT+DMFT: Application to Iron at Core Conditions","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18404","citing_title":"JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18404","citing_title":"JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08885","citing_title":"Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21069","citing_title":"Accelerating point defect simulations using data-driven and machine learning approaches","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA","json":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA.json","graph_json":"https://pith.science/api/pith-number/BDSWREBYIVAUPTLEPE4AKH7LYA/graph.json","events_json":"https://pith.science/api/pith-number/BDSWREBYIVAUPTLEPE4AKH7LYA/events.json","paper":"https://pith.science/paper/BDSWREBY"},"agent_actions":{"view_html":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA","download_json":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA.json","view_paper":"https://pith.science/paper/BDSWREBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16068&json=true","fetch_graph":"https://pith.science/api/pith-number/BDSWREBYIVAUPTLEPE4AKH7LYA/graph.json","fetch_events":"https://pith.science/api/pith-number/BDSWREBYIVAUPTLEPE4AKH7LYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA/action/storage_attestation","attest_author":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA/action/author_attestation","sign_citation":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA/action/citation_signature","submit_replication":"https://pith.science/pith/BDSWREBYIVAUPTLEPE4AKH7LYA/action/replication_record"}},"created_at":"2026-07-05T10:52:34.960258+00:00","updated_at":"2026-07-05T10:52:34.960258+00:00"}