{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RR3XXOYDS7HSCNZYLER3WPU7AS","short_pith_number":"pith:RR3XXOYD","schema_version":"1.0","canonical_sha256":"8c777bbb0397cf2137385923bb3e9f04a9d40b9bf88316be97bbfd75bb703741","source":{"kind":"arxiv","id":"2105.09016","version":4},"attestation_state":"computed","paper":{"title":"E(n) Equivariant Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emiel Hoogeboom, Fabian B. Fuchs, Ingmar Posner, Max Welling, Victor Garcia Satorras","submitted_at":"2021-05-19T09:28:54Z","abstract_excerpt":"This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E(n) graph neural networks and integrate them as a differential equation to obtain an invertible equivariant function: a continuous-time normalizing flow. We demonstrate that E-NFs considerably outperform baselines and existing methods from the literature on particle systems such as DW4 and LJ13, and on molecules from QM9 in terms of log-likelihood. To the best of our knowledge, this is the first flow that jointly generates mol"},"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":"2105.09016","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-19T09:28:54Z","cross_cats_sorted":["physics.chem-ph","stat.ML"],"title_canon_sha256":"8223eddb5c0e38086cdab578522c9a6666c6884597bd768e096b92afeed1a68d","abstract_canon_sha256":"099c3b5ae9f64268e8bc63f641e516cff9fe4c97d4bc570304bc15d1a765239c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:29.243428Z","signature_b64":"vMwofdDMR8oXA/5hnJMHCuKFCcEBBlEViiZ1v6LMoLz4M30WcOZS1l7Cvm01tKuSGiCcuAK+PcMY/W9BDFBECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c777bbb0397cf2137385923bb3e9f04a9d40b9bf88316be97bbfd75bb703741","last_reissued_at":"2026-07-05T03:48:29.242715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:29.242715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E(n) Equivariant Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emiel Hoogeboom, Fabian B. Fuchs, Ingmar Posner, Max Welling, Victor Garcia Satorras","submitted_at":"2021-05-19T09:28:54Z","abstract_excerpt":"This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E(n) graph neural networks and integrate them as a differential equation to obtain an invertible equivariant function: a continuous-time normalizing flow. We demonstrate that E-NFs considerably outperform baselines and existing methods from the literature on particle systems such as DW4 and LJ13, and on molecules from QM9 in terms of log-likelihood. To the best of our knowledge, this is the first flow that jointly generates mol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09016","kind":"arxiv","version":4},"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/2105.09016/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":"2105.09016","created_at":"2026-07-05T03:48:29.242773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.09016v4","created_at":"2026-07-05T03:48:29.242773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09016","created_at":"2026-07-05T03:48:29.242773+00:00"},{"alias_kind":"pith_short_12","alias_value":"RR3XXOYDS7HS","created_at":"2026-07-05T03:48:29.242773+00:00"},{"alias_kind":"pith_short_16","alias_value":"RR3XXOYDS7HSCNZY","created_at":"2026-07-05T03:48:29.242773+00:00"},{"alias_kind":"pith_short_8","alias_value":"RR3XXOYD","created_at":"2026-07-05T03:48:29.242773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.09673","citing_title":"Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS","json":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS.json","graph_json":"https://pith.science/api/pith-number/RR3XXOYDS7HSCNZYLER3WPU7AS/graph.json","events_json":"https://pith.science/api/pith-number/RR3XXOYDS7HSCNZYLER3WPU7AS/events.json","paper":"https://pith.science/paper/RR3XXOYD"},"agent_actions":{"view_html":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS","download_json":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS.json","view_paper":"https://pith.science/paper/RR3XXOYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.09016&json=true","fetch_graph":"https://pith.science/api/pith-number/RR3XXOYDS7HSCNZYLER3WPU7AS/graph.json","fetch_events":"https://pith.science/api/pith-number/RR3XXOYDS7HSCNZYLER3WPU7AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS/action/storage_attestation","attest_author":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS/action/author_attestation","sign_citation":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS/action/citation_signature","submit_replication":"https://pith.science/pith/RR3XXOYDS7HSCNZYLER3WPU7AS/action/replication_record"}},"created_at":"2026-07-05T03:48:29.242773+00:00","updated_at":"2026-07-05T03:48:29.242773+00:00"}