{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXYMFCXGLR64A54KEPEI4SZ3SE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"320e5d1866539d2a729f4d88c6e4cfa9b5e520f74aefe0dc4ceb421caf689f47","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T17:55:44Z","title_canon_sha256":"1c3f023caa01bfb64bada2e04dd35c9a4097c1cdd04f26a21e0ee5a20e00e813"},"schema_version":"1.0","source":{"id":"2409.08262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08262","created_at":"2026-07-05T09:47:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08262v2","created_at":"2026-07-05T09:47:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08262","created_at":"2026-07-05T09:47:34Z"},{"alias_kind":"pith_short_12","alias_value":"LXYMFCXGLR64","created_at":"2026-07-05T09:47:34Z"},{"alias_kind":"pith_short_16","alias_value":"LXYMFCXGLR64A54K","created_at":"2026-07-05T09:47:34Z"},{"alias_kind":"pith_short_8","alias_value":"LXYMFCXG","created_at":"2026-07-05T09:47:34Z"}],"graph_snapshots":[{"event_id":"sha256:fc9ef3d1245744e8d9603d9a24e0a8b247ba2646bbcc7f2b93dbf8a05cc54ad7","target":"graph","created_at":"2026-07-05T09:47:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.08262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Incomplete LU factorizations of sparse matrices are widely used as preconditioners in Krylov subspace methods to speed up solving linear systems. Unfortunately, computing the preconditioner itself can be time-consuming and sensitive to hyper-parameters. Instead, we replace the hand-engineered algorithm with a graph neural network that is trained to approximate the matrix factorization directly. To apply the output of the neural network as a preconditioner, we propose an output activation function that guarantees that the predicted factorization is invertible. Further, applying a graph neural n","authors_text":"Aleix Nieto Juscafresa, Jens Sj\\\"olund, Paul H\\\"ausner","cross_cats":["cs.NA","math.NA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T17:55:44Z","title":"Learning incomplete factorization preconditioners for GMRES"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08262","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e76beb5e1949b0742fc9a8841a36e7bbf305fd98bf1de16d5797a4928614a292","target":"record","created_at":"2026-07-05T09:47:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"320e5d1866539d2a729f4d88c6e4cfa9b5e520f74aefe0dc4ceb421caf689f47","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T17:55:44Z","title_canon_sha256":"1c3f023caa01bfb64bada2e04dd35c9a4097c1cdd04f26a21e0ee5a20e00e813"},"schema_version":"1.0","source":{"id":"2409.08262","kind":"arxiv","version":2}},"canonical_sha256":"5df0c28ae65c7dc0778a23c88e4b3b913ade79617bdbafd78f6b7b36aea7c265","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5df0c28ae65c7dc0778a23c88e4b3b913ade79617bdbafd78f6b7b36aea7c265","first_computed_at":"2026-07-05T09:47:34.720813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:34.720813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1LKIa+mknNCj12zSsNX6MH7i6REJ2odHB9yc8vzIzYr3TikQNDTOGRDsOnk8Ixfz3FSdMNU9fFqFvO2WpjbLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:34.721347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e76beb5e1949b0742fc9a8841a36e7bbf305fd98bf1de16d5797a4928614a292","sha256:fc9ef3d1245744e8d9603d9a24e0a8b247ba2646bbcc7f2b93dbf8a05cc54ad7"],"state_sha256":"3a74e68f7a2c155d45a609e1c85a75ba5adf6c7c0ed7a7680720cd932d8962f7"}