{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","short_pith_number":"pith:667CMDK5","canonical_record":{"source":{"id":"2605.19867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-19T13:58:31Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"129e8d262e3a5eff097fa3f438d90eecf8a25aa8a1fc03ad0e78cd916453481c","abstract_canon_sha256":"d0d91c096d41f88974e263e4cf3e563bfa0f34e1025726bf1e5853cea25d3265"},"schema_version":"1.0"},"canonical_sha256":"f7be260d5d7b053fbba32caa66be74116464f16548f70d2be8778043948b1455","source":{"kind":"arxiv","id":"2605.19867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19867","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19867v1","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19867","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"667CMDK5PMCT","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"667CMDK5PMCT7O5D","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"667CMDK5","created_at":"2026-05-20T01:06:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-19T13:58:31Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"129e8d262e3a5eff097fa3f438d90eecf8a25aa8a1fc03ad0e78cd916453481c","abstract_canon_sha256":"d0d91c096d41f88974e263e4cf3e563bfa0f34e1025726bf1e5853cea25d3265"},"schema_version":"1.0"},"canonical_sha256":"f7be260d5d7b053fbba32caa66be74116464f16548f70d2be8778043948b1455","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:18.289451Z","signature_b64":"5EgSf8b3VCMpPXViFJEdRp+38eczKmw8sx+tQTo3YdK7T92YvTxYOhh+Pn0+P0Ii8OHU48GYPO8BiZ1Z63mnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7be260d5d7b053fbba32caa66be74116464f16548f70d2be8778043948b1455","last_reissued_at":"2026-05-20T01:06:18.288792Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:18.288792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19867","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":"2026-05-20T01:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kBG4i/Dp15lImh0OezQzk5BPRX1QgGUwZ3o891MbsX6ZT8NMryOvy1aNieUZwA+73ysvwmk2iH03e4aKZrsxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.004274Z"},"content_sha256":"c6463cfadc65d0e6135e131d635c81d0280109a23a2cdeb8e957c58fe1f4579b","schema_version":"1.0","event_id":"sha256:c6463cfadc65d0e6135e131d635c81d0280109a23a2cdeb8e957c58fe1f4579b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When can a neural operator replace a coarse solve? Architectural principles for two-level preconditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Hugo Melchers, Michael Abdelmalik, Victorita Dolean","submitted_at":"2026-05-19T13:58:31Z","abstract_excerpt":"Neural operators are increasingly used as drop-in accelerators inside classical numerical methods, but it is rarely clear which architectural ingredients matter for which role. We answer this question for one important role: the coarse-space correction inside a two-level preconditioner for discretised linear partial differential equations. By systematically varying four DeepONet-like architectures along two design axes - input discretisation (sampling versus integration against a basis) and source-term linearity - we show that the favourable corner of this 2$\\times$2 design is occupied by a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19867","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/2605.19867/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":"2026-05-20T01:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqhd1nce+85tqV97UGgo2etsvRu9DTOYp66potSSjjtQkVmOpMKaQHs/uTELoqhJ2QTOoQ2//pXDnUW/v3bBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.004990Z"},"content_sha256":"bc0b1b1e7c3a27251478e5cc0120669912588ff80b43552a767a1c0ba19d43d2","schema_version":"1.0","event_id":"sha256:bc0b1b1e7c3a27251478e5cc0120669912588ff80b43552a767a1c0ba19d43d2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"Identifier '10.48550/arxiv.2602.06842.url:http://arxiv.org/abs/2602.06842' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Y. Wu et al. “Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter”. In: arXiv:2602.06842 (2026). arXiv:2602.06842 [math].doi:10.48550/arXiv.2602.06842.url:http://arxiv.org/abs/2602.06842","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"doi":"10.48550/arxiv.2602.06842.url:http://arxiv.org/abs/2602.06842","arxiv_id":null,"ref_index":55,"raw_excerpt":"Y. Wu et al. “Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter”. In: arXiv:2602.06842 (2026). arXiv:2602.06842 [math].doi:10.48550/arXiv.2602.06842.url:http://arxiv.org/abs/2602.06842","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":55,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arxiv.2602.06842.url:http://arxiv.org/abs/2602.06842","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"43af5c73bdff18ae2925bb41977ef65b88cb7e8bcba4902a6ffd13f3d772fe6b","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4191,"payload_sha256":"ac291c5614b5098af47bb4cd4b7844db935c5717983255daa0e1fd0291204d0e","signature_b64":"swgycMcBn/kxxDINVL9/7kq2VuZN0b86rYZKAlASf7M/V3GIzEGdX9PxDeO5PMoxXE6pviRzFPF0mC8xjDmYCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aL+6R5LQ6ANFW3psgJGV86A82RGqUo7785DxDgFArYhxFDhmixzgXTG9b0J7JfjCv8gfo6BObyJVXTpfeFnVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.006616Z"},"content_sha256":"2f6d9209e811d9b4ecf1aec6b0fa0d5ffddc30e66f73989260edcdc10f02479f","schema_version":"1.0","event_id":"sha256:2f6d9209e811d9b4ecf1aec6b0fa0d5ffddc30e66f73989260edcdc10f02479f"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1515/cmam-2025-0170/html) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"V. Trifonov et al. “Learning from linear algebra: A graph neural network approach to precon- ditioner design for conjugate gradient solvers”. In:Computational Methods in Applied Math- ematics0 (2026).url:https://www.degruyterbrill.com/docum","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"ref_index":52,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"V. Trifonov et al. “Learning from linear algebra: A graph neural network approach to precon- ditioner design for conjugate gradient solvers”. In:Computational Methods in Applied Math- ematics0 (2026).url:https://www.degruyterbrill.com/docum","reconstructed_doi":"10.1515/cmam-2025-0170/html"},"severity":"advisory","ref_index":52,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.1515/cmam-2025-0170/html","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"824812f4e3f206399b9101cc325d0bf4b8fd3c13d33f44346988562390cd3ec7","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4190,"payload_sha256":"fb4f0086faca30463d1496d580ecbb048b99c2cce2975331a24b179686df660e","signature_b64":"vLGt/6sW2s4WfpRaWio+HHsD22EX2aWB3gmrqjft89fjx8dO2ZyTZ9eoHa8SCT10aUBg4y3LOILK8bTL9Ef7Cw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjRuic86EZksn48MxY8hgWuc/yA5F32KjLdtbCQlw6+XJtHr9t49uvegppRetw0gTSteYuq7J5TCuuC0zvhmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.007177Z"},"content_sha256":"2123935dd4a713fde99bca0eba11e4febfc3c6a65486844832a87729b953d016","schema_version":"1.0","event_id":"sha256:2123935dd4a713fde99bca0eba11e4febfc3c6a65486844832a87729b953d016"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"Identifier '10.48550/arxiv.2412.07127.url:http://arxiv.org/abs/2412.07127' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"R. Li, S. Wang, and C. Wang. “Deep Learning-Enhanced Preconditioning for Efficient Con- jugate Gradient Solvers in Large-Scale PDE Systems”. In:arXiv preprint arXiv:2412.07127 [cs](2024).doi:10.48550/arXiv.2412.07127.url:http://arxiv.org/ab","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"doi":"10.48550/arxiv.2412.07127.url:http://arxiv.org/abs/2412.07127","arxiv_id":null,"ref_index":31,"raw_excerpt":"R. Li, S. Wang, and C. Wang. “Deep Learning-Enhanced Preconditioning for Efficient Con- jugate Gradient Solvers in Large-Scale PDE Systems”. In:arXiv preprint arXiv:2412.07127 [cs](2024).doi:10.48550/arXiv.2412.07127.url:http://arxiv.org/abs/2412.07127","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":31,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arxiv.2412.07127.url:http://arxiv.org/abs/2412.07127","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"40907b56f2ecc6fe8fc5d367f7818cc92cd63b2d4c7030d65b0399c174161b6b","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4189,"payload_sha256":"e96947b79398ee478d73fd42f51ae23b708b4f48a51c3126287704b6b618455b","signature_b64":"AGuaeZqs94DujQbllgITEvd0DJFGXt1wHYdwgLKgqkJS0p67fe6l8GaVU4SlEkT7SqMXeca81nuVoZNs/6LGCQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9eG+2ice1lpda8kyFNDBptlhXoo6gY3CRBVEDWDcITLPREhZSgEf003tAIQ5CJ4LC8eMO6TqP0rzukNJvOiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.007769Z"},"content_sha256":"089a022b7464f02ae55350fe8dae2b4fa8e5e484411db2213664711df5b5ebc2","schema_version":"1.0","event_id":"sha256:089a022b7464f02ae55350fe8dae2b4fa8e5e484411db2213664711df5b5ebc2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2508.00101.url:http://arxiv.org/abs/2508.00101) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"A. Kopaniˇ c´ akov´ a, Y. Lee, and G.E. Karniadakis. “Leveraging Operator Learning to Acceler- ate Convergence of the Preconditioned Conjugate Gradient Method”. In: arXiv:2508.00101 (2025). arXiv:2508.00101 [math].doi:10.48550/arXiv.2508.00","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"ref_index":28,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"A. Kopaniˇ c´ akov´ a, Y. Lee, and G.E. Karniadakis. “Leveraging Operator Learning to Acceler- ate Convergence of the Preconditioned Conjugate Gradient Method”. In: arXiv:2508.00101 (2025). arXiv:2508.00101 [math].doi:10.48550/arXiv.2508.00","reconstructed_doi":"10.48550/arXiv.2508.00101.url:http://arxiv.org/abs/2508.00101"},"severity":"advisory","ref_index":28,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2508.00101.url:http://arxiv.org/abs/2508.00101","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"0e9afdeaa1324596048753839520cf28fb998697550ac88b6e5b7e69e8f0538e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4188,"payload_sha256":"aa840d3b43a8b0e41043aa7495d78c9fdce825b43b2b0ccb064c5aa25170f23c","signature_b64":"uJ1SzWW3pM9z92u1AdU+FtpYpFPTiNIB4nPWBgcbDXfOU8rbSf00fqeFWxNIR9WQZ0asagj3nznGz58mMGlBCw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOxeI9hF4qu/GEDdT+w118aekhGt9/nkeARRqZIOTDaj1TAWAlpQOjVu1gkogMtOBf/C3OFbAmk/b98ytiCKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.008312Z"},"content_sha256":"7282c75b93be146c887d278123afe7b93dd792b27f8fdf0a7607a2b4e7b9ec23","schema_version":"1.0","event_id":"sha256:7282c75b93be146c887d278123afe7b93dd792b27f8fdf0a7607a2b4e7b9ec23"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1090/mcom/4086.doi:https://doi.org/10.1090/mcom/4086.url:https://www.ams.org/mcom/0000-000-00/S0025-5718-2025-04086-9/) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"J. Hu and P. Jin. “A hybrid iterative method based on MIONet for PDEs: Theory and numerical examples”. In:Mathematics of Computation(2025). Published electronically. DOI https://doi.org/10.1090/mcom/4086.doi:https://doi.org/10.1090/mcom/408","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"ref_index":23,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"J. Hu and P. Jin. “A hybrid iterative method based on MIONet for PDEs: Theory and numerical examples”. In:Mathematics of Computation(2025). Published electronically. DOI https://doi.org/10.1090/mcom/4086.doi:https://doi.org/10.1090/mcom/408","reconstructed_doi":"10.1090/mcom/4086.doi:https://doi.org/10.1090/mcom/4086.url:https://www.ams.org/mcom/0000-000-00/S0025-5718-2025-04086-9/"},"severity":"advisory","ref_index":23,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.1090/mcom/4086.doi:https://doi.org/10.1090/mcom/4086.url:https://www.ams.org/mcom/0000-000-00/S0025-5718-2025-04086-9/","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"4591f033e005653b3aebf3458e73da20d8d0974103e47b75899d5802f266cc03","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4187,"payload_sha256":"f24778c99af86a5b13a1dc8d245419d4f13ed5d82728d194b17acb5e08d520f0","signature_b64":"E1OHTLgg1J2kEcyaJ7pLqjx9K9RuMGG5GpevM1HHFhwNvBaRO1xBOyUNmpAnnSWn4yaMwsA+u9p5M/77cCqfDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ww3pY0OR1YSAs39GSD0mphOznVuCn8K1j1sN1/7Q1/C5TvXEP6JBgkGpJ2EBA2dyudcAlQJoW35BAYWmH0HHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.008887Z"},"content_sha256":"07a8d54059a55aba41da4e485480e75405738ff3304bb22616582c51d3ae41d2","schema_version":"1.0","event_id":"sha256:07a8d54059a55aba41da4e485480e75405738ff3304bb22616582c51d3ae41d2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2305.16368.url:http://arxiv.org/abs/2305.16368.26) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"P. H¨ ausner, O. ¨Oktem, and J. Sj¨ olund. “Neural incomplete factorization: learning precondi- tioners for the conjugate gradient method”. en. In:arXiv preprint arXiv:2305.16368 [math] (2024).doi:10.48550/arXiv.2305.16368.url:http://arxiv.","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"ref_index":20,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"P. H¨ ausner, O. ¨Oktem, and J. Sj¨ olund. “Neural incomplete factorization: learning precondi- tioners for the conjugate gradient method”. en. In:arXiv preprint arXiv:2305.16368 [math] (2024).doi:10.48550/arXiv.2305.16368.url:http://arxiv.","reconstructed_doi":"10.48550/arXiv.2305.16368.url:http://arxiv.org/abs/2305.16368.26"},"severity":"advisory","ref_index":20,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2305.16368.url:http://arxiv.org/abs/2305.16368.26","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"f7ff445cc466139f9a2ab9a5622d98ddde21bb2b6bfed371d20469eafbbfdee7","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4186,"payload_sha256":"601024649b9ec168fbfbc17d0e30af5afc0bd2bd2a82f0f6af786bed8f230c3a","signature_b64":"6KpiWBmTQnp1PlK0DbfMRBBYGHqlN6QfX2ul4clJbk6aG7hF4EoiZ2aQ+vhizCxaqEpQ7gV0O19ryyNro3VUDg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRvz8uGo5EfjV3mKKM+rXl2v17K55PZbh4TEHi4DRyshio0ZfUJtnsGb18r1YYDXlCAAXVA/EUI3B0ecrc2LDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.009434Z"},"content_sha256":"2cd259bbac2245f62976c68120a9037048f3e0ace07889291eb51a445bafcf26","schema_version":"1.0","event_id":"sha256:2cd259bbac2245f62976c68120a9037048f3e0ace07889291eb51a445bafcf26"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2209.01231.url:http://arxiv.org/abs/2209.01231) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"M. Embree. “How Descriptive are GMRES Convergence Bounds?” In: arXiv:2209.01231 (2022). arXiv:2209.01231 [math].doi:10.48550/arXiv.2209.01231.url:http://arxiv. org/abs/2209.01231","arxiv_id":"2605.19867","detector":"doi_compliance","evidence":{"ref_index":14,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"M. Embree. “How Descriptive are GMRES Convergence Bounds?” In: arXiv:2209.01231 (2022). arXiv:2209.01231 [math].doi:10.48550/arXiv.2209.01231.url:http://arxiv. org/abs/2209.01231","reconstructed_doi":"10.48550/arXiv.2209.01231.url:http://arxiv.org/abs/2209.01231"},"severity":"advisory","ref_index":14,"audited_at":"2026-05-20T02:05:03.777993Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2209.01231.url:http://arxiv.org/abs/2209.01231","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"6d1ade83dc780167fe842e2ece4c56ffd053081e1ba377c314283bcb738d1310","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4185,"payload_sha256":"60c2eec0bfa6369e329ee69456ba8c7a9473bfc1473e7e7685a124c8f3d21527","signature_b64":"I/1+7XXTPesJIcjcaDzakRlr7bFkUzboE2BniCTiIYCkzNxp+Kc70rSvZrepKQe2AQclJS6sIjo4Bj0atovjCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xm90egykyJkrESeMtqYFO5NT5M8UwGl0xxstat4EmqgNLCfDSfwIO2nPVXmwnKgFUWF0a8Pw2xwwMDzqdWHGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:02:48.009966Z"},"content_sha256":"85eb15db6f1a36f8f2ce503de74912ce6772c5cd7a5d443558564f432b73160c","schema_version":"1.0","event_id":"sha256:85eb15db6f1a36f8f2ce503de74912ce6772c5cd7a5d443558564f432b73160c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/667CMDK5PMCT7O5DFSVGNPTUCF/bundle.json","state_url":"https://pith.science/pith/667CMDK5PMCT7O5DFSVGNPTUCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/667CMDK5PMCT7O5DFSVGNPTUCF/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":"2026-05-21T09:02:48Z","links":{"resolver":"https://pith.science/pith/667CMDK5PMCT7O5DFSVGNPTUCF","bundle":"https://pith.science/pith/667CMDK5PMCT7O5DFSVGNPTUCF/bundle.json","state":"https://pith.science/pith/667CMDK5PMCT7O5DFSVGNPTUCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/667CMDK5PMCT7O5DFSVGNPTUCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:667CMDK5PMCT7O5DFSVGNPTUCF","merge_version":"pith-open-graph-merge-v1","event_count":9,"valid_event_count":9,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d0d91c096d41f88974e263e4cf3e563bfa0f34e1025726bf1e5853cea25d3265","cross_cats_sorted":["cs.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-19T13:58:31Z","title_canon_sha256":"129e8d262e3a5eff097fa3f438d90eecf8a25aa8a1fc03ad0e78cd916453481c"},"schema_version":"1.0","source":{"id":"2605.19867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19867","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19867v1","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19867","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"667CMDK5PMCT","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"667CMDK5PMCT7O5D","created_at":"2026-05-20T01:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"667CMDK5","created_at":"2026-05-20T01:06:18Z"}],"graph_snapshots":[{"event_id":"sha256:bc0b1b1e7c3a27251478e5cc0120669912588ff80b43552a767a1c0ba19d43d2","target":"graph","created_at":"2026-05-20T01:06:18Z","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/2605.19867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural operators are increasingly used as drop-in accelerators inside classical numerical methods, but it is rarely clear which architectural ingredients matter for which role. We answer this question for one important role: the coarse-space correction inside a two-level preconditioner for discretised linear partial differential equations. By systematically varying four DeepONet-like architectures along two design axes - input discretisation (sampling versus integration against a basis) and source-term linearity - we show that the favourable corner of this 2$\\times$2 design is occupied by a si","authors_text":"Hugo Melchers, Michael Abdelmalik, Victorita Dolean","cross_cats":["cs.NA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-19T13:58:31Z","title":"When can a neural operator replace a coarse solve? Architectural principles for two-level preconditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19867","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:c6463cfadc65d0e6135e131d635c81d0280109a23a2cdeb8e957c58fe1f4579b","target":"record","created_at":"2026-05-20T01:06:18Z","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":"d0d91c096d41f88974e263e4cf3e563bfa0f34e1025726bf1e5853cea25d3265","cross_cats_sorted":["cs.NA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2026-05-19T13:58:31Z","title_canon_sha256":"129e8d262e3a5eff097fa3f438d90eecf8a25aa8a1fc03ad0e78cd916453481c"},"schema_version":"1.0","source":{"id":"2605.19867","kind":"arxiv","version":1}},"canonical_sha256":"f7be260d5d7b053fbba32caa66be74116464f16548f70d2be8778043948b1455","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7be260d5d7b053fbba32caa66be74116464f16548f70d2be8778043948b1455","first_computed_at":"2026-05-20T01:06:18.288792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:18.288792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5EgSf8b3VCMpPXViFJEdRp+38eczKmw8sx+tQTo3YdK7T92YvTxYOhh+Pn0+P0Ii8OHU48GYPO8BiZ1Z63mnAA==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:18.289451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19867","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:07a8d54059a55aba41da4e485480e75405738ff3304bb22616582c51d3ae41d2","sha256:089a022b7464f02ae55350fe8dae2b4fa8e5e484411db2213664711df5b5ebc2","sha256:2123935dd4a713fde99bca0eba11e4febfc3c6a65486844832a87729b953d016","sha256:2cd259bbac2245f62976c68120a9037048f3e0ace07889291eb51a445bafcf26","sha256:2f6d9209e811d9b4ecf1aec6b0fa0d5ffddc30e66f73989260edcdc10f02479f","sha256:7282c75b93be146c887d278123afe7b93dd792b27f8fdf0a7607a2b4e7b9ec23","sha256:85eb15db6f1a36f8f2ce503de74912ce6772c5cd7a5d443558564f432b73160c"]}],"invalid_events":[],"applied_event_ids":["sha256:c6463cfadc65d0e6135e131d635c81d0280109a23a2cdeb8e957c58fe1f4579b","sha256:bc0b1b1e7c3a27251478e5cc0120669912588ff80b43552a767a1c0ba19d43d2"],"state_sha256":"fd4fff6eb5a3ed48ca8869e48ee24b64e7a56f5f9fecbf0feb364764164f7fe4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XlpVxxbkD3GZei0yKU1bX4N8hyzAeUhEyYDes8P2aWQbY/Jx9GUnVgL3507FQBARKpLczpZlhHva3dFyq0NBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T09:02:48.015367Z","bundle_sha256":"93ad144c944f316f825a2190bac4612bed38e87d99fb2532aa1a13978dc340bf"}}