{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VV3MOQTY6AJHWOUBOHKJLVAD2W","short_pith_number":"pith:VV3MOQTY","schema_version":"1.0","canonical_sha256":"ad76c74278f0127b3a8171d495d403d599d5ca977f6f72338a333b9f4097694e","source":{"kind":"arxiv","id":"2205.11393","version":2},"attestation_state":"computed","paper":{"title":"Generic bounds on the approximation error for physics-informed (and) operator learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Siddhartha Mishra, Tim De Ryck","submitted_at":"2022-05-23T15:40:33Z","abstract_excerpt":"We propose a very general framework for deriving rigorous bounds on the approximation error for physics-informed neural networks (PINNs) and operator learning architectures such as DeepONets and FNOs as well as for physics-informed operator learning. These bounds guarantee that PINNs and (physics-informed) DeepONets or FNOs will efficiently approximate the underlying solution or solution operator of generic partial differential equations (PDEs). Our framework utilizes existing neural network approximation results to obtain bounds on more involved learning architectures for PDEs. We illustrate "},"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":"2205.11393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T15:40:33Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"d1f83859cc8a6767b6a2ff2af619ebab38784642d833de5610303f9fd816c12c","abstract_canon_sha256":"09dcd171ad0eda7047877784d5a7d11bac8287eeff9ee673bd1de0a6a650faa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:48.687715Z","signature_b64":"xWi5q2kiQTCZU8Gx6zJv1WCexYkY/QIMJPfPAH1xZBaz0pAhpQIVb4OdrRawcMhGYHrbthBgnztl2ztyO/bSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad76c74278f0127b3a8171d495d403d599d5ca977f6f72338a333b9f4097694e","last_reissued_at":"2026-07-05T05:04:48.687169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:48.687169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generic bounds on the approximation error for physics-informed (and) operator learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Siddhartha Mishra, Tim De Ryck","submitted_at":"2022-05-23T15:40:33Z","abstract_excerpt":"We propose a very general framework for deriving rigorous bounds on the approximation error for physics-informed neural networks (PINNs) and operator learning architectures such as DeepONets and FNOs as well as for physics-informed operator learning. These bounds guarantee that PINNs and (physics-informed) DeepONets or FNOs will efficiently approximate the underlying solution or solution operator of generic partial differential equations (PDEs). Our framework utilizes existing neural network approximation results to obtain bounds on more involved learning architectures for PDEs. We illustrate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11393","kind":"arxiv","version":2},"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/2205.11393/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":"2205.11393","created_at":"2026-07-05T05:04:48.687230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11393v2","created_at":"2026-07-05T05:04:48.687230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11393","created_at":"2026-07-05T05:04:48.687230+00:00"},{"alias_kind":"pith_short_12","alias_value":"VV3MOQTY6AJH","created_at":"2026-07-05T05:04:48.687230+00:00"},{"alias_kind":"pith_short_16","alias_value":"VV3MOQTY6AJHWOUB","created_at":"2026-07-05T05:04:48.687230+00:00"},{"alias_kind":"pith_short_8","alias_value":"VV3MOQTY","created_at":"2026-07-05T05:04:48.687230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12050","citing_title":"Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02475","citing_title":"Physics-Informed Residuals for Adaptive Mesh Refinement in Finite-Difference PDE Solvers","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W","json":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W.json","graph_json":"https://pith.science/api/pith-number/VV3MOQTY6AJHWOUBOHKJLVAD2W/graph.json","events_json":"https://pith.science/api/pith-number/VV3MOQTY6AJHWOUBOHKJLVAD2W/events.json","paper":"https://pith.science/paper/VV3MOQTY"},"agent_actions":{"view_html":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W","download_json":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W.json","view_paper":"https://pith.science/paper/VV3MOQTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11393&json=true","fetch_graph":"https://pith.science/api/pith-number/VV3MOQTY6AJHWOUBOHKJLVAD2W/graph.json","fetch_events":"https://pith.science/api/pith-number/VV3MOQTY6AJHWOUBOHKJLVAD2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W/action/storage_attestation","attest_author":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W/action/author_attestation","sign_citation":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W/action/citation_signature","submit_replication":"https://pith.science/pith/VV3MOQTY6AJHWOUBOHKJLVAD2W/action/replication_record"}},"created_at":"2026-07-05T05:04:48.687230+00:00","updated_at":"2026-07-05T05:04:48.687230+00:00"}