{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:COL2OX2NGUN7OP4MRF65UJ4F3K","short_pith_number":"pith:COL2OX2N","schema_version":"1.0","canonical_sha256":"1397a75f4d351bf73f8c897dda2785da836e17107dadfe2bcbac18ab14d93d6e","source":{"kind":"arxiv","id":"2411.13848","version":1},"attestation_state":"computed","paper":{"title":"Exact and approximate error bounds for physics-informed neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Augusto T. Chantada, Claudia G. Sc\\'occola, Luca Gomez Bachar, Pavlos Protopapas, Susana J. Landau","submitted_at":"2024-11-21T05:15:28Z","abstract_excerpt":"The use of neural networks to solve differential equations, as an alternative to traditional numerical solvers, has increased recently. However, error bounds for the obtained solutions have only been developed for certain equations. In this work, we report important progress in calculating error bounds of physics-informed neural networks (PINNs) solutions of nonlinear first-order ODEs. We give a general expression that describes the error of the solution that the PINN-based method provides for a nonlinear first-order ODE. In addition, we propose a technique to calculate an approximate bound fo"},"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":"2411.13848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T05:15:28Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"58eb55bd6fb708bdada3ee15dfdaff2307900acaa4ab78e398a8f047520182cb","abstract_canon_sha256":"27f58f2304c1f9f286261f5371a86734c02cc8baa889e53d0eb078fe6960e227"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:37.993506Z","signature_b64":"zDPGtilz9/ZLmVuwk7DXpc9U9RjBNgJp06DkqM4F6jgqYucKonwzQDvgNtx58BBe/RRpZ7KM+7IqVLUG+HNtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1397a75f4d351bf73f8c897dda2785da836e17107dadfe2bcbac18ab14d93d6e","last_reissued_at":"2026-07-05T09:38:37.993013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:37.993013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exact and approximate error bounds for physics-informed neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Augusto T. Chantada, Claudia G. Sc\\'occola, Luca Gomez Bachar, Pavlos Protopapas, Susana J. Landau","submitted_at":"2024-11-21T05:15:28Z","abstract_excerpt":"The use of neural networks to solve differential equations, as an alternative to traditional numerical solvers, has increased recently. However, error bounds for the obtained solutions have only been developed for certain equations. In this work, we report important progress in calculating error bounds of physics-informed neural networks (PINNs) solutions of nonlinear first-order ODEs. We give a general expression that describes the error of the solution that the PINN-based method provides for a nonlinear first-order ODE. In addition, we propose a technique to calculate an approximate bound fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13848","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/2411.13848/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":"2411.13848","created_at":"2026-07-05T09:38:37.993072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13848v1","created_at":"2026-07-05T09:38:37.993072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13848","created_at":"2026-07-05T09:38:37.993072+00:00"},{"alias_kind":"pith_short_12","alias_value":"COL2OX2NGUN7","created_at":"2026-07-05T09:38:37.993072+00:00"},{"alias_kind":"pith_short_16","alias_value":"COL2OX2NGUN7OP4M","created_at":"2026-07-05T09:38:37.993072+00:00"},{"alias_kind":"pith_short_8","alias_value":"COL2OX2N","created_at":"2026-07-05T09:38:37.993072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06038","citing_title":"Fredholm Neural Networks for inverse problems in elliptic PDEs","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K","json":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K.json","graph_json":"https://pith.science/api/pith-number/COL2OX2NGUN7OP4MRF65UJ4F3K/graph.json","events_json":"https://pith.science/api/pith-number/COL2OX2NGUN7OP4MRF65UJ4F3K/events.json","paper":"https://pith.science/paper/COL2OX2N"},"agent_actions":{"view_html":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K","download_json":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K.json","view_paper":"https://pith.science/paper/COL2OX2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13848&json=true","fetch_graph":"https://pith.science/api/pith-number/COL2OX2NGUN7OP4MRF65UJ4F3K/graph.json","fetch_events":"https://pith.science/api/pith-number/COL2OX2NGUN7OP4MRF65UJ4F3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K/action/storage_attestation","attest_author":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K/action/author_attestation","sign_citation":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K/action/citation_signature","submit_replication":"https://pith.science/pith/COL2OX2NGUN7OP4MRF65UJ4F3K/action/replication_record"}},"created_at":"2026-07-05T09:38:37.993072+00:00","updated_at":"2026-07-05T09:38:37.993072+00:00"}