{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2B4OZILB6CSO2RLWYRZOMT2S4W","short_pith_number":"pith:2B4OZILB","schema_version":"1.0","canonical_sha256":"d078eca161f0a4ed4576c472e64f52e5beeda782df5ac961c28e5d4ad645919f","source":{"kind":"arxiv","id":"1906.01200","version":1},"attestation_state":"computed","paper":{"title":"Learning Neural PDE Solvers with Convergence Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","stat.CO","stat.ML"],"primary_cat":"math.NA","authors_text":"Jun-Ting Hsieh, Lucia Mirabella, Shengjia Zhao, Stefano Ermon, Stephan Eismann","submitted_at":"2019-06-04T05:28:22Z","abstract_excerpt":"Partial differential equations (PDEs) are widely used across the physical and computational sciences. Decades of research and engineering went into designing fast iterative solution methods. Existing solvers are general purpose, but may be sub-optimal for specific classes of problems. In contrast to existing hand-crafted solutions, we propose an approach to learn a fast iterative solver tailored to a specific domain. We achieve this goal by learning to modify the updates of an existing solver using a deep neural network. Crucially, our approach is proven to preserve strong correctness and conv"},"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":"1906.01200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2019-06-04T05:28:22Z","cross_cats_sorted":["cs.NA","stat.CO","stat.ML"],"title_canon_sha256":"174854b55d4f4447e63fc3a0177d7b2e64e0f263db36e54ccd5e78e6304663b7","abstract_canon_sha256":"08b3b14e7d5064415e1961e760a9a3dae7ca373bb4eed1aee8fab04e153faf4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:44.202692Z","signature_b64":"94ogkD9Bns+yEGIYD/iknMC0ep52WHBthtCHlP8ySl0AmzZNkCDEItqzI6RIGnwNieCB+cD4TAJPhKSL0wgLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d078eca161f0a4ed4576c472e64f52e5beeda782df5ac961c28e5d4ad645919f","last_reissued_at":"2026-07-05T09:09:44.202280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:44.202280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Neural PDE Solvers with Convergence Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","stat.CO","stat.ML"],"primary_cat":"math.NA","authors_text":"Jun-Ting Hsieh, Lucia Mirabella, Shengjia Zhao, Stefano Ermon, Stephan Eismann","submitted_at":"2019-06-04T05:28:22Z","abstract_excerpt":"Partial differential equations (PDEs) are widely used across the physical and computational sciences. Decades of research and engineering went into designing fast iterative solution methods. Existing solvers are general purpose, but may be sub-optimal for specific classes of problems. In contrast to existing hand-crafted solutions, we propose an approach to learn a fast iterative solver tailored to a specific domain. We achieve this goal by learning to modify the updates of an existing solver using a deep neural network. Crucially, our approach is proven to preserve strong correctness and conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01200","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/1906.01200/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":"1906.01200","created_at":"2026-07-05T09:09:44.202335+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01200v1","created_at":"2026-07-05T09:09:44.202335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01200","created_at":"2026-07-05T09:09:44.202335+00:00"},{"alias_kind":"pith_short_12","alias_value":"2B4OZILB6CSO","created_at":"2026-07-05T09:09:44.202335+00:00"},{"alias_kind":"pith_short_16","alias_value":"2B4OZILB6CSO2RLW","created_at":"2026-07-05T09:09:44.202335+00:00"},{"alias_kind":"pith_short_8","alias_value":"2B4OZILB","created_at":"2026-07-05T09:09:44.202335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2302.03286","citing_title":"Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19867","citing_title":"When can a neural operator replace a coarse solve? Architectural principles for two-level preconditioning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02481","citing_title":"NOWS: Neural Operator Warm Starts for Accelerating Iterative Solvers","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W","json":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W.json","graph_json":"https://pith.science/api/pith-number/2B4OZILB6CSO2RLWYRZOMT2S4W/graph.json","events_json":"https://pith.science/api/pith-number/2B4OZILB6CSO2RLWYRZOMT2S4W/events.json","paper":"https://pith.science/paper/2B4OZILB"},"agent_actions":{"view_html":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W","download_json":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W.json","view_paper":"https://pith.science/paper/2B4OZILB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01200&json=true","fetch_graph":"https://pith.science/api/pith-number/2B4OZILB6CSO2RLWYRZOMT2S4W/graph.json","fetch_events":"https://pith.science/api/pith-number/2B4OZILB6CSO2RLWYRZOMT2S4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W/action/storage_attestation","attest_author":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W/action/author_attestation","sign_citation":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W/action/citation_signature","submit_replication":"https://pith.science/pith/2B4OZILB6CSO2RLWYRZOMT2S4W/action/replication_record"}},"created_at":"2026-07-05T09:09:44.202335+00:00","updated_at":"2026-07-05T09:09:44.202335+00:00"}