{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SCGAG3PDOJ53LU3A2L6OLS6CPK","short_pith_number":"pith:SCGAG3PD","schema_version":"1.0","canonical_sha256":"908c036de3727bb5d360d2fce5cbc27aa31a12357b4b1956c0cee7541c9cd4f3","source":{"kind":"arxiv","id":"2603.19165","version":1},"attestation_state":"computed","paper":{"title":"Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees","license":"","headline":"","cross_cats":["math.AP","math.FA"],"primary_cat":"cs.LG","authors_text":"Amartya Mukherjee, David C. Del Rey Fernández, Jun Liu, Maxwell Fitzsimmons","submitted_at":"2026-03-19T17:19:48Z","abstract_excerpt":"Uncertainty quantification for partial differential equations is traditionally grounded in discretization theory, where solution error is controlled via mesh/grid refinement. Physics-informed neural networks fundamentally depart from this paradigm: they approximate solutions by minimizing residual losses at collocation points, introducing new sources of error arising from optimization, sampling, representation, and overfitting. As a result, the generalization error in the solution space remains an open problem. Our main theoretical contribution establishes generalization bounds that connect re"},"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":"2603.19165","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.LG","submitted_at":"2026-03-19T17:19:48Z","cross_cats_sorted":["math.AP","math.FA"],"title_canon_sha256":"aedf7bff3e5007ccdb082f301b8d33204c564c9e15046daac6aa73dbfce2b06f","abstract_canon_sha256":"71142a7dfecad20f7ea8503114dae942801dc8a464bcd3cb413d1f526aa6876d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T08:42:25.893482Z","signature_b64":"RLDYdhEMuflSvqyN2FBDqvWcgPUgD1P7FawWkQlc4tE0/LGCVN9UINKRQIDg8qc+NuShoYrsNDY4i0rnQgzpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"908c036de3727bb5d360d2fce5cbc27aa31a12357b4b1956c0cee7541c9cd4f3","last_reissued_at":"2026-07-02T08:42:25.892927Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T08:42:25.892927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees","license":"","headline":"","cross_cats":["math.AP","math.FA"],"primary_cat":"cs.LG","authors_text":"Amartya Mukherjee, David C. Del Rey Fernández, Jun Liu, Maxwell Fitzsimmons","submitted_at":"2026-03-19T17:19:48Z","abstract_excerpt":"Uncertainty quantification for partial differential equations is traditionally grounded in discretization theory, where solution error is controlled via mesh/grid refinement. Physics-informed neural networks fundamentally depart from this paradigm: they approximate solutions by minimizing residual losses at collocation points, introducing new sources of error arising from optimization, sampling, representation, and overfitting. As a result, the generalization error in the solution space remains an open problem. Our main theoretical contribution establishes generalization bounds that connect re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19165","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/2603.19165/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":"2603.19165","created_at":"2026-07-02T08:42:25.892996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.19165v1","created_at":"2026-07-02T08:42:25.892996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19165","created_at":"2026-07-02T08:42:25.892996+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCGAG3PDOJ53","created_at":"2026-07-02T08:42:25.892996+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCGAG3PDOJ53LU3A","created_at":"2026-07-02T08:42:25.892996+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCGAG3PD","created_at":"2026-07-02T08:42:25.892996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK","json":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK.json","graph_json":"https://pith.science/api/pith-number/SCGAG3PDOJ53LU3A2L6OLS6CPK/graph.json","events_json":"https://pith.science/api/pith-number/SCGAG3PDOJ53LU3A2L6OLS6CPK/events.json","paper":"https://pith.science/paper/SCGAG3PD"},"agent_actions":{"view_html":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK","download_json":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK.json","view_paper":"https://pith.science/paper/SCGAG3PD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.19165&json=true","fetch_graph":"https://pith.science/api/pith-number/SCGAG3PDOJ53LU3A2L6OLS6CPK/graph.json","fetch_events":"https://pith.science/api/pith-number/SCGAG3PDOJ53LU3A2L6OLS6CPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK/action/storage_attestation","attest_author":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK/action/author_attestation","sign_citation":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK/action/citation_signature","submit_replication":"https://pith.science/pith/SCGAG3PDOJ53LU3A2L6OLS6CPK/action/replication_record"}},"created_at":"2026-07-02T08:42:25.892996+00:00","updated_at":"2026-07-02T08:42:25.892996+00:00"}