{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CDKUQBLPU6TSXDRR37YMZRLYE","short_pith_number":"pith:2CDKUQBL","schema_version":"1.0","canonical_sha256":"d086aa402b7d3d395c718eff86662bc12bddecd574cacf0616fdfb3ca2cdd433","source":{"kind":"arxiv","id":"2409.20264","version":1},"attestation_state":"computed","paper":{"title":"First Order System Least Squares Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Christoph Schwab, Joost A. A. Opschoor, Philipp C. Petersen","submitted_at":"2024-09-30T13:04:35Z","abstract_excerpt":"We introduce a conceptual framework for numerically solving linear elliptic, parabolic, and hyperbolic PDEs on bounded, polytopal domains in euclidean spaces by deep neural networks. The PDEs are recast as minimization of a least-squares (LSQ for short) residual of an equivalent, well-posed first-order system, over parametric families of deep neural networks. The associated LSQ residual is a) equal or proportional to a weak residual of the PDE, b) additive in terms of contributions from localized subnetworks, indicating locally ``out-of-equilibrium'' of neural networks with respect to the PDE "},"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":"2409.20264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2024-09-30T13:04:35Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"5cb265eb0cc56350cf63a0d4544a71ece45e21d0abd167617d3db77da16aa58d","abstract_canon_sha256":"044f34379082cbd5ac273458992a7085c435e81526383593c4433294a0ca6612"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:41.104531Z","signature_b64":"+UCPmzJQ/LKZsqUcKdJpEPeV0Q7OpbvIJ4IbOrEqWZsptOL2D2QogmyeL7B4TwJowAj5NCnb0nstJK+fdz3ADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d086aa402b7d3d395c718eff86662bc12bddecd574cacf0616fdfb3ca2cdd433","last_reissued_at":"2026-07-05T09:13:41.104139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:41.104139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First Order System Least Squares Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Christoph Schwab, Joost A. A. Opschoor, Philipp C. Petersen","submitted_at":"2024-09-30T13:04:35Z","abstract_excerpt":"We introduce a conceptual framework for numerically solving linear elliptic, parabolic, and hyperbolic PDEs on bounded, polytopal domains in euclidean spaces by deep neural networks. The PDEs are recast as minimization of a least-squares (LSQ for short) residual of an equivalent, well-posed first-order system, over parametric families of deep neural networks. The associated LSQ residual is a) equal or proportional to a weak residual of the PDE, b) additive in terms of contributions from localized subnetworks, indicating locally ``out-of-equilibrium'' of neural networks with respect to the PDE "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20264","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/2409.20264/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":"2409.20264","created_at":"2026-07-05T09:13:41.104192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20264v1","created_at":"2026-07-05T09:13:41.104192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20264","created_at":"2026-07-05T09:13:41.104192+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CDKUQBLPU6T","created_at":"2026-07-05T09:13:41.104192+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CDKUQBLPU6TSXDR","created_at":"2026-07-05T09:13:41.104192+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CDKUQBL","created_at":"2026-07-05T09:13:41.104192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.20336","citing_title":"A posteriori certification of PDE approximations with particular application to neural networks","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE","json":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE.json","graph_json":"https://pith.science/api/pith-number/2CDKUQBLPU6TSXDRR37YMZRLYE/graph.json","events_json":"https://pith.science/api/pith-number/2CDKUQBLPU6TSXDRR37YMZRLYE/events.json","paper":"https://pith.science/paper/2CDKUQBL"},"agent_actions":{"view_html":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE","download_json":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE.json","view_paper":"https://pith.science/paper/2CDKUQBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20264&json=true","fetch_graph":"https://pith.science/api/pith-number/2CDKUQBLPU6TSXDRR37YMZRLYE/graph.json","fetch_events":"https://pith.science/api/pith-number/2CDKUQBLPU6TSXDRR37YMZRLYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE/action/storage_attestation","attest_author":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE/action/author_attestation","sign_citation":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE/action/citation_signature","submit_replication":"https://pith.science/pith/2CDKUQBLPU6TSXDRR37YMZRLYE/action/replication_record"}},"created_at":"2026-07-05T09:13:41.104192+00:00","updated_at":"2026-07-05T09:13:41.104192+00:00"}