{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LGCADI7LIPD2RHY52X4TGAT4J3","short_pith_number":"pith:LGCADI7L","schema_version":"1.0","canonical_sha256":"598401a3eb43c7a89f1dd5f933027c4efdaa8e214845d9bab0fac316feec5b73","source":{"kind":"arxiv","id":"2508.00101","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Operator Learning to Accelerate Convergence of the Preconditioned Conjugate Gradient Method","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC"],"primary_cat":"math.NA","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, George Em Karniadakis, Youngkyu Lee","submitted_at":"2025-07-31T18:53:23Z","abstract_excerpt":"We propose a new deflation strategy to accelerate the convergence of the preconditioned conjugate gradient(PCG) method for solving parametric large-scale linear systems of equations. Unlike traditional deflation techniques that rely on eigenvector approximations or recycled Krylov subspaces, we generate the deflation subspaces using operator learning, specifically the Deep Operator Network~(DeepONet). To this aim, we introduce two complementary approaches for assembling the deflation operators. The first approach approximates near-null space vectors of the discrete PDE operator using the basis"},"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":"2508.00101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-31T18:53:23Z","cross_cats_sorted":["cs.LG","cs.NA","math.OC"],"title_canon_sha256":"393492cda7966f7eab25f6c32c725f576e44ec16090905f12905de614e7ad13f","abstract_canon_sha256":"6a2862630024d31e00b5a64161130632bc4db5c3780831330104ab592b288964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:48.898548Z","signature_b64":"uqmN7tlnO8W0nnmg8kkHIsSOdfIKGzUDhU5isq9I6QNBmF+ikZ9FUGqsFawRHQkobSgA7zi6Wy01eQFQuQP/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"598401a3eb43c7a89f1dd5f933027c4efdaa8e214845d9bab0fac316feec5b73","last_reissued_at":"2026-07-05T11:46:48.898072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:48.898072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Operator Learning to Accelerate Convergence of the Preconditioned Conjugate Gradient Method","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC"],"primary_cat":"math.NA","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, George Em Karniadakis, Youngkyu Lee","submitted_at":"2025-07-31T18:53:23Z","abstract_excerpt":"We propose a new deflation strategy to accelerate the convergence of the preconditioned conjugate gradient(PCG) method for solving parametric large-scale linear systems of equations. Unlike traditional deflation techniques that rely on eigenvector approximations or recycled Krylov subspaces, we generate the deflation subspaces using operator learning, specifically the Deep Operator Network~(DeepONet). To this aim, we introduce two complementary approaches for assembling the deflation operators. The first approach approximates near-null space vectors of the discrete PDE operator using the basis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00101","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/2508.00101/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":"2508.00101","created_at":"2026-07-05T11:46:48.898133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00101v1","created_at":"2026-07-05T11:46:48.898133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00101","created_at":"2026-07-05T11:46:48.898133+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGCADI7LIPD2","created_at":"2026-07-05T11:46:48.898133+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGCADI7LIPD2RHY5","created_at":"2026-07-05T11:46:48.898133+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGCADI7L","created_at":"2026-07-05T11:46:48.898133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19867","citing_title":"When can a neural operator replace a coarse solve? Architectural principles for two-level preconditioning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02481","citing_title":"NOWS: Neural Operator Warm Starts for Accelerating Iterative Solvers","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3","json":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3.json","graph_json":"https://pith.science/api/pith-number/LGCADI7LIPD2RHY52X4TGAT4J3/graph.json","events_json":"https://pith.science/api/pith-number/LGCADI7LIPD2RHY52X4TGAT4J3/events.json","paper":"https://pith.science/paper/LGCADI7L"},"agent_actions":{"view_html":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3","download_json":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3.json","view_paper":"https://pith.science/paper/LGCADI7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00101&json=true","fetch_graph":"https://pith.science/api/pith-number/LGCADI7LIPD2RHY52X4TGAT4J3/graph.json","fetch_events":"https://pith.science/api/pith-number/LGCADI7LIPD2RHY52X4TGAT4J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3/action/storage_attestation","attest_author":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3/action/author_attestation","sign_citation":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3/action/citation_signature","submit_replication":"https://pith.science/pith/LGCADI7LIPD2RHY52X4TGAT4J3/action/replication_record"}},"created_at":"2026-07-05T11:46:48.898133+00:00","updated_at":"2026-07-05T11:46:48.898133+00:00"}