{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J6C2OSXMURNY3XCSSYJIYARJUW","short_pith_number":"pith:J6C2OSXM","schema_version":"1.0","canonical_sha256":"4f85a74aeca45b8ddc5296128c0229a5924a52ad122707ca0b83045f28529941","source":{"kind":"arxiv","id":"2404.01145","version":1},"attestation_state":"computed","paper":{"title":"Sequential-in-time training of nonlinear parametrizations for solving time-dependent partial differential equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Benjamin Peherstorfer, Eric Vanden-Eijnden, Huan Zhang, Yifan Chen","submitted_at":"2024-04-01T14:45:16Z","abstract_excerpt":"Sequential-in-time methods solve a sequence of training problems to fit nonlinear parametrizations such as neural networks to approximate solution trajectories of partial differential equations over time. This work shows that sequential-in-time training methods can be understood broadly as either optimize-then-discretize (OtD) or discretize-then-optimize (DtO) schemes, which are well known concepts in numerical analysis. The unifying perspective leads to novel stability and a posteriori error analysis results that provide insights into theoretical and numerical aspects that are inherent to eit"},"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":"2404.01145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2024-04-01T14:45:16Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"a13e88c2bde142524a5d8f70e8a97a9c8044e6ac692d178f06fe1a8c43f8c4b0","abstract_canon_sha256":"be5748ea9cc03d9295dd1aeafa5a7e9b08850f88826d226a49d1e96cbbb9b516"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:01.485813Z","signature_b64":"WDBslIbAAEP5O+oPnR9jDSl2Opq4U+ryif27palOPReI60C2BN/OlixUXvCKMGKzo/AzH0/yZCv50wAZ+BblDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f85a74aeca45b8ddc5296128c0229a5924a52ad122707ca0b83045f28529941","last_reissued_at":"2026-07-05T08:03:01.485366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:01.485366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential-in-time training of nonlinear parametrizations for solving time-dependent partial differential equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Benjamin Peherstorfer, Eric Vanden-Eijnden, Huan Zhang, Yifan Chen","submitted_at":"2024-04-01T14:45:16Z","abstract_excerpt":"Sequential-in-time methods solve a sequence of training problems to fit nonlinear parametrizations such as neural networks to approximate solution trajectories of partial differential equations over time. This work shows that sequential-in-time training methods can be understood broadly as either optimize-then-discretize (OtD) or discretize-then-optimize (DtO) schemes, which are well known concepts in numerical analysis. The unifying perspective leads to novel stability and a posteriori error analysis results that provide insights into theoretical and numerical aspects that are inherent to eit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01145","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/2404.01145/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":"2404.01145","created_at":"2026-07-05T08:03:01.485427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01145v1","created_at":"2026-07-05T08:03:01.485427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01145","created_at":"2026-07-05T08:03:01.485427+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6C2OSXMURNY","created_at":"2026-07-05T08:03:01.485427+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6C2OSXMURNY3XCS","created_at":"2026-07-05T08:03:01.485427+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6C2OSXM","created_at":"2026-07-05T08:03:01.485427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04920","citing_title":"PINNs in PDE Constrained Optimal Control Problems: Direct vs Indirect Methods","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW","json":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW.json","graph_json":"https://pith.science/api/pith-number/J6C2OSXMURNY3XCSSYJIYARJUW/graph.json","events_json":"https://pith.science/api/pith-number/J6C2OSXMURNY3XCSSYJIYARJUW/events.json","paper":"https://pith.science/paper/J6C2OSXM"},"agent_actions":{"view_html":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW","download_json":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW.json","view_paper":"https://pith.science/paper/J6C2OSXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01145&json=true","fetch_graph":"https://pith.science/api/pith-number/J6C2OSXMURNY3XCSSYJIYARJUW/graph.json","fetch_events":"https://pith.science/api/pith-number/J6C2OSXMURNY3XCSSYJIYARJUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW/action/storage_attestation","attest_author":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW/action/author_attestation","sign_citation":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW/action/citation_signature","submit_replication":"https://pith.science/pith/J6C2OSXMURNY3XCSSYJIYARJUW/action/replication_record"}},"created_at":"2026-07-05T08:03:01.485427+00:00","updated_at":"2026-07-05T08:03:01.485427+00:00"}