{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZP6AFZNEUB4CCGP45E4HHHFXS3","short_pith_number":"pith:ZP6AFZNE","schema_version":"1.0","canonical_sha256":"cbfc02e5a4a0782119fce938739cb796eab2f5be43d7e71dc38675c5eb7eaec6","source":{"kind":"arxiv","id":"2511.16171","version":2},"attestation_state":"computed","paper":{"title":"Shallow neural network yields regularization for ill-posed inverse problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Bangti Jin, Lan Wang, Qiao Zhu, Ye Zhang","submitted_at":"2025-11-20T09:16:43Z","abstract_excerpt":"In this paper, we develop a regularization theory for neural network approximations of general ill-posed operator equations with noisy data. Within the framework of iterative regularization, we introduce two expanding neural network methods (ENNs) under different a priori assumptions on the exact solution. Instead of prescribing a fixed architecture, ENNs adaptively select the number of neurons through an a posteriori stopping rule, so that the selected network size serves as a regularization parameter balancing approximation accuracy and stability with respect to data noise. We prove the regu"},"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":"2511.16171","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2025-11-20T09:16:43Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"c13a315c4ec05758ddabc65adb920ab130267b991712a44eef9118a11688e289","abstract_canon_sha256":"fa8da5c9e2c980c9a4ae900dc55482a29caa491f77a0afdf91f1426997796de8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:16.840981Z","signature_b64":"+keGipA4eZbhahDH0skLKWcPi+TgBsY0r3XjThLFD+fMk7g4amaQwELMm02mxMHQmqwJ0W6rwUos8AnGQNlQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbfc02e5a4a0782119fce938739cb796eab2f5be43d7e71dc38675c5eb7eaec6","last_reissued_at":"2026-06-12T01:09:16.840090Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:16.840090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shallow neural network yields regularization for ill-posed inverse problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Bangti Jin, Lan Wang, Qiao Zhu, Ye Zhang","submitted_at":"2025-11-20T09:16:43Z","abstract_excerpt":"In this paper, we develop a regularization theory for neural network approximations of general ill-posed operator equations with noisy data. Within the framework of iterative regularization, we introduce two expanding neural network methods (ENNs) under different a priori assumptions on the exact solution. Instead of prescribing a fixed architecture, ENNs adaptively select the number of neurons through an a posteriori stopping rule, so that the selected network size serves as a regularization parameter balancing approximation accuracy and stability with respect to data noise. We prove the regu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16171","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/2511.16171/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":"2511.16171","created_at":"2026-06-12T01:09:16.840190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.16171v2","created_at":"2026-06-12T01:09:16.840190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16171","created_at":"2026-06-12T01:09:16.840190+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZP6AFZNEUB4C","created_at":"2026-06-12T01:09:16.840190+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZP6AFZNEUB4CCGP4","created_at":"2026-06-12T01:09:16.840190+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZP6AFZNE","created_at":"2026-06-12T01:09:16.840190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.00517","citing_title":"Deep neural network yields regularization for ill-posed inverse problems","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3","json":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3.json","graph_json":"https://pith.science/api/pith-number/ZP6AFZNEUB4CCGP45E4HHHFXS3/graph.json","events_json":"https://pith.science/api/pith-number/ZP6AFZNEUB4CCGP45E4HHHFXS3/events.json","paper":"https://pith.science/paper/ZP6AFZNE"},"agent_actions":{"view_html":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3","download_json":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3.json","view_paper":"https://pith.science/paper/ZP6AFZNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.16171&json=true","fetch_graph":"https://pith.science/api/pith-number/ZP6AFZNEUB4CCGP45E4HHHFXS3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZP6AFZNEUB4CCGP45E4HHHFXS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3/action/storage_attestation","attest_author":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3/action/author_attestation","sign_citation":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3/action/citation_signature","submit_replication":"https://pith.science/pith/ZP6AFZNEUB4CCGP45E4HHHFXS3/action/replication_record"}},"created_at":"2026-06-12T01:09:16.840190+00:00","updated_at":"2026-06-12T01:09:16.840190+00:00"}