{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NB3EHH4R475HEJ2DBNU7DTUJEH","short_pith_number":"pith:NB3EHH4R","schema_version":"1.0","canonical_sha256":"6876439f91e7fa7227430b69f1ce8921f7ccfffd6ad0d41c7316d9b459da3f32","source":{"kind":"arxiv","id":"2507.14302","version":1},"attestation_state":"computed","paper":{"title":"A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"physics.chem-ph","authors_text":"Bingqing Cheng, Daniel S. King, Dongjin Kim, Peichen Zhong, Theo Jaffrelot Inizan, Xiaoyu Wang","submitted_at":"2025-07-18T18:21:45Z","abstract_excerpt":"Most current machine learning interatomic potentials (MLIPs) rely on short-range approximations, without explicit treatment of long-range electrostatics. To address this, we recently developed the Latent Ewald Summation (LES) method, which infers electrostatic interactions, polarization, and Born effective charges (BECs), just by learning from energy and force training data. Here, we present LES as a standalone library, compatible with any short-range MLIP, and demonstrate its integration with methods such as MACE, NequIP, CACE, and CHGNet. We benchmark LES-enhanced models on distinct systems,"},"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":"2507.14302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2025-07-18T18:21:45Z","cross_cats_sorted":["cs.LG","physics.comp-ph"],"title_canon_sha256":"a318492e53049b03fcbedc6898f51ebbdf7bad7416f6effff272927f92642a89","abstract_canon_sha256":"2e8dfcd79a72347b5155dba056c2b8827d5dd60ebbb9e93dea91495100a9cb25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:04.068395Z","signature_b64":"r3539M19h9MK8tB0tHm/+o8OUXdx407OzZfYmCDbZXCVJ15v4rALetk1oTxWE9c7bgHAgS68r+zrMTjN9wyeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6876439f91e7fa7227430b69f1ce8921f7ccfffd6ad0d41c7316d9b459da3f32","last_reissued_at":"2026-07-05T11:40:04.067919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:04.067919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"physics.chem-ph","authors_text":"Bingqing Cheng, Daniel S. King, Dongjin Kim, Peichen Zhong, Theo Jaffrelot Inizan, Xiaoyu Wang","submitted_at":"2025-07-18T18:21:45Z","abstract_excerpt":"Most current machine learning interatomic potentials (MLIPs) rely on short-range approximations, without explicit treatment of long-range electrostatics. To address this, we recently developed the Latent Ewald Summation (LES) method, which infers electrostatic interactions, polarization, and Born effective charges (BECs), just by learning from energy and force training data. Here, we present LES as a standalone library, compatible with any short-range MLIP, and demonstrate its integration with methods such as MACE, NequIP, CACE, and CHGNet. We benchmark LES-enhanced models on distinct systems,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14302","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/2507.14302/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":"2507.14302","created_at":"2026-07-05T11:40:04.067974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14302v1","created_at":"2026-07-05T11:40:04.067974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14302","created_at":"2026-07-05T11:40:04.067974+00:00"},{"alias_kind":"pith_short_12","alias_value":"NB3EHH4R475H","created_at":"2026-07-05T11:40:04.067974+00:00"},{"alias_kind":"pith_short_16","alias_value":"NB3EHH4R475HEJ2D","created_at":"2026-07-05T11:40:04.067974+00:00"},{"alias_kind":"pith_short_8","alias_value":"NB3EHH4R","created_at":"2026-07-05T11:40:04.067974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03656","citing_title":"Simultaneous Learning of Static and Dynamic Charges","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16331","citing_title":"Accuracy and Efficiency Benchmarks of Pretrained Machine Learning Potentials for Molecular Simulations","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH","json":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH.json","graph_json":"https://pith.science/api/pith-number/NB3EHH4R475HEJ2DBNU7DTUJEH/graph.json","events_json":"https://pith.science/api/pith-number/NB3EHH4R475HEJ2DBNU7DTUJEH/events.json","paper":"https://pith.science/paper/NB3EHH4R"},"agent_actions":{"view_html":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH","download_json":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH.json","view_paper":"https://pith.science/paper/NB3EHH4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14302&json=true","fetch_graph":"https://pith.science/api/pith-number/NB3EHH4R475HEJ2DBNU7DTUJEH/graph.json","fetch_events":"https://pith.science/api/pith-number/NB3EHH4R475HEJ2DBNU7DTUJEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH/action/storage_attestation","attest_author":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH/action/author_attestation","sign_citation":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH/action/citation_signature","submit_replication":"https://pith.science/pith/NB3EHH4R475HEJ2DBNU7DTUJEH/action/replication_record"}},"created_at":"2026-07-05T11:40:04.067974+00:00","updated_at":"2026-07-05T11:40:04.067974+00:00"}