{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LBG52634KCQCYYH42PXGFLNVX5","short_pith_number":"pith:LBG52634","canonical_record":{"source":{"id":"2507.15452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-21T10:03:55Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"0c99f4cf35d78e69f5c89614d0f32683d23b7773928952b488502500c42872f2","abstract_canon_sha256":"b316c7f77057e0936002d339de5f732ed039c6b2c73aadfb370d130c949cd6f9"},"schema_version":"1.0"},"canonical_sha256":"584ddd7b7c50a02c60fcd3ee62adb5bf47b94cdd5634cba4b19315f87c81d83b","source":{"kind":"arxiv","id":"2507.15452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15452","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15452v1","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15452","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"pith_short_12","alias_value":"LBG52634KCQC","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"pith_short_16","alias_value":"LBG52634KCQCYYH4","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"pith_short_8","alias_value":"LBG52634","created_at":"2026-07-05T11:40:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LBG52634KCQCYYH42PXGFLNVX5","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-21T10:03:55Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"0c99f4cf35d78e69f5c89614d0f32683d23b7773928952b488502500c42872f2","abstract_canon_sha256":"b316c7f77057e0936002d339de5f732ed039c6b2c73aadfb370d130c949cd6f9"},"schema_version":"1.0"},"canonical_sha256":"584ddd7b7c50a02c60fcd3ee62adb5bf47b94cdd5634cba4b19315f87c81d83b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:37.351892Z","signature_b64":"6ghjbDwxIH9X/NQY0T8+A+FtApnujtFHkfu7bj1F/w0iLkh27YQ35HWKYMagUNZsnRjzpKnV7jb7u1WpKOPdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"584ddd7b7c50a02c60fcd3ee62adb5bf47b94cdd5634cba4b19315f87c81d83b","last_reissued_at":"2026-07-05T11:40:37.351450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:37.351450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15452","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFSYSxw6Noy6+K+FNjKsZLx1KbuBjlO8p72qMj4HCp1vSiZSHccaoaHst51+q/7JB+BZPvH3O+m+CvbZVNpEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:56:19.753516Z"},"content_sha256":"df642d2ec5a9909199a4d94c386a30a144d5fc766edde36648a50be035e57185","schema_version":"1.0","event_id":"sha256:df642d2ec5a9909199a4d94c386a30a144d5fc766edde36648a50be035e57185"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LBG52634KCQCYYH42PXGFLNVX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Preconditioning via Krylov Subspace Geometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Alessandro Coclite, Nunzio Dimola, Paolo Zunino","submitted_at":"2025-07-21T10:03:55Z","abstract_excerpt":"We propose a geometry-aware strategy for training neural preconditioners tailored to parametrized linear systems arising from the discretization of mixed-dimensional partial differential equations (PDEs). These systems are typically ill-conditioned because of the presence of embedded lower-dimensional structures and are solved using Krylov subspace methods. Our approach yields an approximation of the inverse operator employing a learning algorithm consisting of a two-stage training framework: an initial static pre-training phase, based on residual minimization, followed by a dynamic fine-tunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15452","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/2507.15452/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dedeu3DLYql7GpMMeIhiBpPeqIf0LD1EPN3w0IYkKDWD5fOiLxXNZxtDY54RnDBtxHlm2CziUUif98Yfirq4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:56:19.754080Z"},"content_sha256":"a0928ce00a09c08a58bd6dbc78d6d03463fec3b75bf4bc7a0aeedcd91021eaac","schema_version":"1.0","event_id":"sha256:a0928ce00a09c08a58bd6dbc78d6d03463fec3b75bf4bc7a0aeedcd91021eaac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBG52634KCQCYYH42PXGFLNVX5/bundle.json","state_url":"https://pith.science/pith/LBG52634KCQCYYH42PXGFLNVX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBG52634KCQCYYH42PXGFLNVX5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T13:56:19Z","links":{"resolver":"https://pith.science/pith/LBG52634KCQCYYH42PXGFLNVX5","bundle":"https://pith.science/pith/LBG52634KCQCYYH42PXGFLNVX5/bundle.json","state":"https://pith.science/pith/LBG52634KCQCYYH42PXGFLNVX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBG52634KCQCYYH42PXGFLNVX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LBG52634KCQCYYH42PXGFLNVX5","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":"b316c7f77057e0936002d339de5f732ed039c6b2c73aadfb370d130c949cd6f9","cross_cats_sorted":["cs.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-21T10:03:55Z","title_canon_sha256":"0c99f4cf35d78e69f5c89614d0f32683d23b7773928952b488502500c42872f2"},"schema_version":"1.0","source":{"id":"2507.15452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15452","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15452v1","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15452","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"pith_short_12","alias_value":"LBG52634KCQC","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"pith_short_16","alias_value":"LBG52634KCQCYYH4","created_at":"2026-07-05T11:40:37Z"},{"alias_kind":"pith_short_8","alias_value":"LBG52634","created_at":"2026-07-05T11:40:37Z"}],"graph_snapshots":[{"event_id":"sha256:a0928ce00a09c08a58bd6dbc78d6d03463fec3b75bf4bc7a0aeedcd91021eaac","target":"graph","created_at":"2026-07-05T11:40:37Z","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/2507.15452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a geometry-aware strategy for training neural preconditioners tailored to parametrized linear systems arising from the discretization of mixed-dimensional partial differential equations (PDEs). These systems are typically ill-conditioned because of the presence of embedded lower-dimensional structures and are solved using Krylov subspace methods. Our approach yields an approximation of the inverse operator employing a learning algorithm consisting of a two-stage training framework: an initial static pre-training phase, based on residual minimization, followed by a dynamic fine-tunin","authors_text":"Alessandro Coclite, Nunzio Dimola, Paolo Zunino","cross_cats":["cs.NA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-21T10:03:55Z","title":"Neural Preconditioning via Krylov Subspace Geometry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15452","kind":"arxiv","version":1},"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:df642d2ec5a9909199a4d94c386a30a144d5fc766edde36648a50be035e57185","target":"record","created_at":"2026-07-05T11:40:37Z","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":"b316c7f77057e0936002d339de5f732ed039c6b2c73aadfb370d130c949cd6f9","cross_cats_sorted":["cs.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-21T10:03:55Z","title_canon_sha256":"0c99f4cf35d78e69f5c89614d0f32683d23b7773928952b488502500c42872f2"},"schema_version":"1.0","source":{"id":"2507.15452","kind":"arxiv","version":1}},"canonical_sha256":"584ddd7b7c50a02c60fcd3ee62adb5bf47b94cdd5634cba4b19315f87c81d83b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"584ddd7b7c50a02c60fcd3ee62adb5bf47b94cdd5634cba4b19315f87c81d83b","first_computed_at":"2026-07-05T11:40:37.351450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:37.351450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ghjbDwxIH9X/NQY0T8+A+FtApnujtFHkfu7bj1F/w0iLkh27YQ35HWKYMagUNZsnRjzpKnV7jb7u1WpKOPdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:37.351892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df642d2ec5a9909199a4d94c386a30a144d5fc766edde36648a50be035e57185","sha256:a0928ce00a09c08a58bd6dbc78d6d03463fec3b75bf4bc7a0aeedcd91021eaac"],"state_sha256":"03eee23627ce4b9f4f2d41e33cd96097c8872a24f5709918b158d0ec4a61bb49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XG3DJKLCDzAtVevouK6mub3bx0OTmdDeJAFHzEDFNrK8G9A/DNSrl/fFogRo+CC/2gxvVpHHcyQji3V/a+G8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:56:19.758973Z","bundle_sha256":"d0e2e7544911c5df83994cf1be511e4fe7c875a57b8fdc0c024963b1ce73b506"}}