{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NPJSTJXTZVRAWLMWCXK3EMH7KZ","short_pith_number":"pith:NPJSTJXT","schema_version":"1.0","canonical_sha256":"6bd329a6f3cd620b2d9615d5b230ff566bd8e613efcde86f8cb2cdacf9369fc0","source":{"kind":"arxiv","id":"2507.06017","version":1},"attestation_state":"computed","paper":{"title":"A posteriori analysis of neural network approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Sergio Rojas, Thomas F\\\"uhrer","submitted_at":"2025-07-08T14:23:55Z","abstract_excerpt":"In a general setting, we study a posteriori estimates used in finite element analysis to measure the error between a solution and its approximation. The latter is not necessarily generated by a finite element method. We show that the error is equivalent to the sum of two residuals provided that the underlying variational formulation is well posed. The first contribution is the projection of the residual to a finite-dimensional space and is therefore computable, while the second one can be reliably estimated by a computable upper bound in many practical scenarios. Assuming sufficiently accurate"},"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":"2507.06017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2025-07-08T14:23:55Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"144bdca07ddbf16aac714d3a71f0fffd973b6cee87a1e9f76f090dc0e707b8a7","abstract_canon_sha256":"dfdebdd9437f2da7f3523839ffc6fab34f25109dfc1a2747488ed26d26d93115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:39.997069Z","signature_b64":"YfctmOTF81Lnyz5tpFAH1N/zqkT8ifeMrwuPrsfdnGOZnHnpNvwMNU4rgZm2LjhWTThsWxOeKWs+9e/1TNP/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bd329a6f3cd620b2d9615d5b230ff566bd8e613efcde86f8cb2cdacf9369fc0","last_reissued_at":"2026-07-05T11:33:39.996603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:39.996603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A posteriori analysis of neural network approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Sergio Rojas, Thomas F\\\"uhrer","submitted_at":"2025-07-08T14:23:55Z","abstract_excerpt":"In a general setting, we study a posteriori estimates used in finite element analysis to measure the error between a solution and its approximation. The latter is not necessarily generated by a finite element method. We show that the error is equivalent to the sum of two residuals provided that the underlying variational formulation is well posed. The first contribution is the projection of the residual to a finite-dimensional space and is therefore computable, while the second one can be reliably estimated by a computable upper bound in many practical scenarios. Assuming sufficiently accurate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06017","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/2507.06017/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":"2507.06017","created_at":"2026-07-05T11:33:39.996665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06017v1","created_at":"2026-07-05T11:33:39.996665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06017","created_at":"2026-07-05T11:33:39.996665+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPJSTJXTZVRA","created_at":"2026-07-05T11:33:39.996665+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPJSTJXTZVRAWLMW","created_at":"2026-07-05T11:33:39.996665+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPJSTJXT","created_at":"2026-07-05T11:33:39.996665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20972","citing_title":"Neural network approximation in discrete dual norms with adaptive test spaces","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ","json":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ.json","graph_json":"https://pith.science/api/pith-number/NPJSTJXTZVRAWLMWCXK3EMH7KZ/graph.json","events_json":"https://pith.science/api/pith-number/NPJSTJXTZVRAWLMWCXK3EMH7KZ/events.json","paper":"https://pith.science/paper/NPJSTJXT"},"agent_actions":{"view_html":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ","download_json":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ.json","view_paper":"https://pith.science/paper/NPJSTJXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06017&json=true","fetch_graph":"https://pith.science/api/pith-number/NPJSTJXTZVRAWLMWCXK3EMH7KZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NPJSTJXTZVRAWLMWCXK3EMH7KZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ/action/storage_attestation","attest_author":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ/action/author_attestation","sign_citation":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ/action/citation_signature","submit_replication":"https://pith.science/pith/NPJSTJXTZVRAWLMWCXK3EMH7KZ/action/replication_record"}},"created_at":"2026-07-05T11:33:39.996665+00:00","updated_at":"2026-07-05T11:33:39.996665+00:00"}