{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HJ5BNCTXU5BYAXMH23GRSPPDCB","short_pith_number":"pith:HJ5BNCTX","schema_version":"1.0","canonical_sha256":"3a7a168a77a743805d87d6cd193de31062b1ccc59dd78b3e07a131513e926c87","source":{"kind":"arxiv","id":"2104.02903","version":4},"attestation_state":"computed","paper":{"title":"A Priori Analysis of Stable Neural Network Solutions to Numerical PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Jinchao Xu, Jonathan W. Siegel, Qingguo Hong","submitted_at":"2021-04-07T04:02:59Z","abstract_excerpt":"Methods for solving PDEs using neural networks have recently become a very important topic. We provide an a priori error analysis for such methods which is based on the $\\mathcal{K}_1(\\mathbb{D})$-norm of the solution. We show that the resulting constrained optimization problem can be efficiently solved using a greedy algorithm, which replaces stochastic gradient descent. Following this, we show that the error arising from discretizing the energy integrals is bounded both in the deterministic case, i.e. when using numerical quadrature, and also in the stochastic case, i.e. when sampling points"},"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":"2104.02903","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2021-04-07T04:02:59Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"c18302383539704fa4e8f229fd1daa914fbd321d4f6231e1c78977ba6cd969fb","abstract_canon_sha256":"c8427ae08ac3b5303c3274fd0196fe287d8b16f0ce975d1baec416bcbaf90293"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:06.819844Z","signature_b64":"Y+mfEPCslES1EtVKS0DikoyH5KRHz634zP2geC8NS6ew+TbT5Uqvy7Zn81vy8OvFEdOdK2EAOctWj3MiyQKzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a7a168a77a743805d87d6cd193de31062b1ccc59dd78b3e07a131513e926c87","last_reissued_at":"2026-07-05T04:40:06.819523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:06.819523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Priori Analysis of Stable Neural Network Solutions to Numerical PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Jinchao Xu, Jonathan W. Siegel, Qingguo Hong","submitted_at":"2021-04-07T04:02:59Z","abstract_excerpt":"Methods for solving PDEs using neural networks have recently become a very important topic. We provide an a priori error analysis for such methods which is based on the $\\mathcal{K}_1(\\mathbb{D})$-norm of the solution. We show that the resulting constrained optimization problem can be efficiently solved using a greedy algorithm, which replaces stochastic gradient descent. Following this, we show that the error arising from discretizing the energy integrals is bounded both in the deterministic case, i.e. when using numerical quadrature, and also in the stochastic case, i.e. when sampling points"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02903","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/2104.02903/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":"2104.02903","created_at":"2026-07-05T04:40:06.819568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02903v4","created_at":"2026-07-05T04:40:06.819568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02903","created_at":"2026-07-05T04:40:06.819568+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJ5BNCTXU5BY","created_at":"2026-07-05T04:40:06.819568+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJ5BNCTXU5BYAXMH","created_at":"2026-07-05T04:40:06.819568+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJ5BNCTX","created_at":"2026-07-05T04:40:06.819568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03521","citing_title":"PINN-DG: Residual neural network methods trained with Finite Elements","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB","json":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB.json","graph_json":"https://pith.science/api/pith-number/HJ5BNCTXU5BYAXMH23GRSPPDCB/graph.json","events_json":"https://pith.science/api/pith-number/HJ5BNCTXU5BYAXMH23GRSPPDCB/events.json","paper":"https://pith.science/paper/HJ5BNCTX"},"agent_actions":{"view_html":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB","download_json":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB.json","view_paper":"https://pith.science/paper/HJ5BNCTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02903&json=true","fetch_graph":"https://pith.science/api/pith-number/HJ5BNCTXU5BYAXMH23GRSPPDCB/graph.json","fetch_events":"https://pith.science/api/pith-number/HJ5BNCTXU5BYAXMH23GRSPPDCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB/action/storage_attestation","attest_author":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB/action/author_attestation","sign_citation":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB/action/citation_signature","submit_replication":"https://pith.science/pith/HJ5BNCTXU5BYAXMH23GRSPPDCB/action/replication_record"}},"created_at":"2026-07-05T04:40:06.819568+00:00","updated_at":"2026-07-05T04:40:06.819568+00:00"}