{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KFYR626QPZ4YS2EGKJCQ7JAHAS","short_pith_number":"pith:KFYR626Q","schema_version":"1.0","canonical_sha256":"51711f6bd07e7989688652450fa40704b6ae314e51c3bce3f78f184bfad7bca1","source":{"kind":"arxiv","id":"2405.15557","version":3},"attestation_state":"computed","paper":{"title":"Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Alexander Rudikov, Ekaterina Muravleva, Ivan Oseledets, Oleg Iliev, Vladislav Trifonov, Yuri M. Laevsky","submitted_at":"2024-05-24T13:44:30Z","abstract_excerpt":"Large linear systems are ubiquitous in modern computational science and engineering. The main recipe for solving them is the use of Krylov subspace iterative methods with well-designed preconditioners. Recently, GNNs have been shown to be a promising tool for designing preconditioners to reduce the overall computational cost of iterative methods by constructing them more efficiently than with classical linear algebra techniques. Preconditioners designed with these approaches cannot outperform those designed with classical methods in terms of the number of iterations in CG. In our work, we reca"},"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":"2405.15557","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T13:44:30Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"5f14265fd7751b6e60aea5b049c90209ca50b1679bf1ec458994b6700067398b","abstract_canon_sha256":"b6c886f99ceedf24d91f16b818b757344f2448f8a518148fe2bef6240f52c14c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:17.143374Z","signature_b64":"K5pGKaX6/KSpjpmYzceJf3bBqc9jNjhYiOqQd+8iEU+ZiRe6DPFF2NEVJ4Wit2KRd6gZpYtIRqrD4gbv49yGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51711f6bd07e7989688652450fa40704b6ae314e51c3bce3f78f184bfad7bca1","last_reissued_at":"2026-07-05T10:08:17.142903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:17.142903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Alexander Rudikov, Ekaterina Muravleva, Ivan Oseledets, Oleg Iliev, Vladislav Trifonov, Yuri M. Laevsky","submitted_at":"2024-05-24T13:44:30Z","abstract_excerpt":"Large linear systems are ubiquitous in modern computational science and engineering. The main recipe for solving them is the use of Krylov subspace iterative methods with well-designed preconditioners. Recently, GNNs have been shown to be a promising tool for designing preconditioners to reduce the overall computational cost of iterative methods by constructing them more efficiently than with classical linear algebra techniques. Preconditioners designed with these approaches cannot outperform those designed with classical methods in terms of the number of iterations in CG. In our work, we reca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15557","kind":"arxiv","version":3},"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/2405.15557/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":"2405.15557","created_at":"2026-07-05T10:08:17.142960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15557v3","created_at":"2026-07-05T10:08:17.142960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15557","created_at":"2026-07-05T10:08:17.142960+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFYR626QPZ4Y","created_at":"2026-07-05T10:08:17.142960+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFYR626QPZ4YS2EG","created_at":"2026-07-05T10:08:17.142960+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFYR626Q","created_at":"2026-07-05T10:08:17.142960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22742","citing_title":"Factored Sparse Approximate Inverse Preconditioning via Spectral Optimization","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS","json":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS.json","graph_json":"https://pith.science/api/pith-number/KFYR626QPZ4YS2EGKJCQ7JAHAS/graph.json","events_json":"https://pith.science/api/pith-number/KFYR626QPZ4YS2EGKJCQ7JAHAS/events.json","paper":"https://pith.science/paper/KFYR626Q"},"agent_actions":{"view_html":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS","download_json":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS.json","view_paper":"https://pith.science/paper/KFYR626Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15557&json=true","fetch_graph":"https://pith.science/api/pith-number/KFYR626QPZ4YS2EGKJCQ7JAHAS/graph.json","fetch_events":"https://pith.science/api/pith-number/KFYR626QPZ4YS2EGKJCQ7JAHAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS/action/storage_attestation","attest_author":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS/action/author_attestation","sign_citation":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS/action/citation_signature","submit_replication":"https://pith.science/pith/KFYR626QPZ4YS2EGKJCQ7JAHAS/action/replication_record"}},"created_at":"2026-07-05T10:08:17.142960+00:00","updated_at":"2026-07-05T10:08:17.142960+00:00"}