{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BXBPGBB44MYSJWIFCTYR4J4CX6","short_pith_number":"pith:BXBPGBB4","schema_version":"1.0","canonical_sha256":"0dc2f3043ce33124d90514f11e2782bf8445943812a2ad46efbce284b195ab9b","source":{"kind":"arxiv","id":"2404.10771","version":2},"attestation_state":"computed","paper":{"title":"TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Di Luo, Esteban Vizcaino, Jacob McCarran, Marin Solja\\v{c}i\\'c, Zhuo Chen","submitted_at":"2024-04-16T17:55:31Z","abstract_excerpt":"Partial differential equations (PDEs) are instrumental for modeling dynamical systems in science and engineering. The advent of neural networks has initiated a significant shift in tackling these complexities though challenges in accuracy persist, especially for initial value problems. In this paper, we introduce the $\\textit{Time-Evolving Natural Gradient (TENG)}$, generalizing time-dependent variational principles and optimization-based time integration, leveraging natural gradient optimization to obtain high accuracy in neural-network-based PDE solutions. Our comprehensive development inclu"},"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":"2404.10771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T17:55:31Z","cross_cats_sorted":["cs.NA","math.NA","physics.comp-ph"],"title_canon_sha256":"1f7435d1d4c9300606841b5c3eda9a7b84342db142addcd0ff58118015a8ec17","abstract_canon_sha256":"748ef5ca8d2377faa7eaf76a690ba2db5ac79c1180f7838af0b9e3f6221a2f68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:09.282607Z","signature_b64":"j//9kTfTVod8O/2CqLGi4krkoApH4QbXxhcdHXjAMRJ0gBqLhyDpmwdAbMmOA/2si/5yHfQQvyDAqJziEIAbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc2f3043ce33124d90514f11e2782bf8445943812a2ad46efbce284b195ab9b","last_reissued_at":"2026-07-05T08:28:09.282179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:09.282179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Di Luo, Esteban Vizcaino, Jacob McCarran, Marin Solja\\v{c}i\\'c, Zhuo Chen","submitted_at":"2024-04-16T17:55:31Z","abstract_excerpt":"Partial differential equations (PDEs) are instrumental for modeling dynamical systems in science and engineering. The advent of neural networks has initiated a significant shift in tackling these complexities though challenges in accuracy persist, especially for initial value problems. In this paper, we introduce the $\\textit{Time-Evolving Natural Gradient (TENG)}$, generalizing time-dependent variational principles and optimization-based time integration, leveraging natural gradient optimization to obtain high accuracy in neural-network-based PDE solutions. Our comprehensive development inclu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10771","kind":"arxiv","version":2},"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/2404.10771/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":"2404.10771","created_at":"2026-07-05T08:28:09.282236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10771v2","created_at":"2026-07-05T08:28:09.282236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10771","created_at":"2026-07-05T08:28:09.282236+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXBPGBB44MYS","created_at":"2026-07-05T08:28:09.282236+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXBPGBB44MYSJWIF","created_at":"2026-07-05T08:28:09.282236+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXBPGBB4","created_at":"2026-07-05T08:28:09.282236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6","json":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6.json","graph_json":"https://pith.science/api/pith-number/BXBPGBB44MYSJWIFCTYR4J4CX6/graph.json","events_json":"https://pith.science/api/pith-number/BXBPGBB44MYSJWIFCTYR4J4CX6/events.json","paper":"https://pith.science/paper/BXBPGBB4"},"agent_actions":{"view_html":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6","download_json":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6.json","view_paper":"https://pith.science/paper/BXBPGBB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10771&json=true","fetch_graph":"https://pith.science/api/pith-number/BXBPGBB44MYSJWIFCTYR4J4CX6/graph.json","fetch_events":"https://pith.science/api/pith-number/BXBPGBB44MYSJWIFCTYR4J4CX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6/action/storage_attestation","attest_author":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6/action/author_attestation","sign_citation":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6/action/citation_signature","submit_replication":"https://pith.science/pith/BXBPGBB44MYSJWIFCTYR4J4CX6/action/replication_record"}},"created_at":"2026-07-05T08:28:09.282236+00:00","updated_at":"2026-07-05T08:28:09.282236+00:00"}