{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CUVRI326GQUGQD7N6WUL7GKODW","short_pith_number":"pith:CUVRI326","schema_version":"1.0","canonical_sha256":"152b146f5e3428680fedf5a8bf994e1d98568d1afe1f4ffa5ff49b19cd1d3599","source":{"kind":"arxiv","id":"2403.09549","version":3},"attestation_state":"computed","paper":{"title":"Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Muhammed Shuaibi, Tess Smidt, Yi-Lun Liao","submitted_at":"2024-03-14T16:38:02Z","abstract_excerpt":"Understanding the interactions of atoms such as forces in 3D atomistic systems is fundamental to many applications like molecular dynamics and catalyst design. However, simulating these interactions requires compute-intensive ab initio calculations and thus results in limited data for training neural networks. In this paper, we propose to use denoising non-equilibrium structures (DeNS) as an auxiliary task to better leverage training data and improve performance. For training with DeNS, we first corrupt a 3D structure by adding noise to its 3D coordinates and then predict the noise. Different "},"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":"2403.09549","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T16:38:02Z","cross_cats_sorted":["cs.AI","physics.chem-ph","physics.comp-ph"],"title_canon_sha256":"236180ed87dd3ac03bf042244881b78d18906df2c77f58d43bc192818958aff3","abstract_canon_sha256":"779848ce90ac2bd17f443b63198d46a790e983230ea1ccadec43d52afde7c653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:10.248131Z","signature_b64":"RTV7esH/P2D0xKXG9yBIlRCm17kZEctL3+30u4NQ2Ctq7QxhsPCbIK8ujvzZpEhM+RqDwcI8AkT9RgMCQEIoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"152b146f5e3428680fedf5a8bf994e1d98568d1afe1f4ffa5ff49b19cd1d3599","last_reissued_at":"2026-07-05T09:52:10.247681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:10.247681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Muhammed Shuaibi, Tess Smidt, Yi-Lun Liao","submitted_at":"2024-03-14T16:38:02Z","abstract_excerpt":"Understanding the interactions of atoms such as forces in 3D atomistic systems is fundamental to many applications like molecular dynamics and catalyst design. However, simulating these interactions requires compute-intensive ab initio calculations and thus results in limited data for training neural networks. In this paper, we propose to use denoising non-equilibrium structures (DeNS) as an auxiliary task to better leverage training data and improve performance. For training with DeNS, we first corrupt a 3D structure by adding noise to its 3D coordinates and then predict the noise. Different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09549","kind":"arxiv","version":3},"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/2403.09549/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":"2403.09549","created_at":"2026-07-05T09:52:10.247736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09549v3","created_at":"2026-07-05T09:52:10.247736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09549","created_at":"2026-07-05T09:52:10.247736+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUVRI326GQUG","created_at":"2026-07-05T09:52:10.247736+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUVRI326GQUGQD7N","created_at":"2026-07-05T09:52:10.247736+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUVRI326","created_at":"2026-07-05T09:52:10.247736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.12771","citing_title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12771","citing_title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW","json":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW.json","graph_json":"https://pith.science/api/pith-number/CUVRI326GQUGQD7N6WUL7GKODW/graph.json","events_json":"https://pith.science/api/pith-number/CUVRI326GQUGQD7N6WUL7GKODW/events.json","paper":"https://pith.science/paper/CUVRI326"},"agent_actions":{"view_html":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW","download_json":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW.json","view_paper":"https://pith.science/paper/CUVRI326","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09549&json=true","fetch_graph":"https://pith.science/api/pith-number/CUVRI326GQUGQD7N6WUL7GKODW/graph.json","fetch_events":"https://pith.science/api/pith-number/CUVRI326GQUGQD7N6WUL7GKODW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW/action/storage_attestation","attest_author":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW/action/author_attestation","sign_citation":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW/action/citation_signature","submit_replication":"https://pith.science/pith/CUVRI326GQUGQD7N6WUL7GKODW/action/replication_record"}},"created_at":"2026-07-05T09:52:10.247736+00:00","updated_at":"2026-07-05T09:52:10.247736+00:00"}