{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MJ6AYCOVJF7DZTCTDRWFW6KXA3","short_pith_number":"pith:MJ6AYCOV","schema_version":"1.0","canonical_sha256":"627c0c09d5497e3ccc531c6c5b795706fc148d4fad98c1a6ac1a76586fa5079a","source":{"kind":"arxiv","id":"2606.00517","version":1},"attestation_state":"computed","paper":{"title":"Deep 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":"Lan Wang, Qiao Zhu, Ye Zhang","submitted_at":"2026-05-30T04:15:23Z","abstract_excerpt":"This paper studies the regularization of ill-posed inverse problems by deep neural networks (DNNs). We extend architecture-based regularization from shallow networks to deep models by developing a deterministic framework in which the admissible network class is enlarged adaptively and the resulting architecture complexity acts as the regularization mechanism. We propose two discrepancy-principle-driven expanding DNN algorithms to treat the cases where an explicit parameter-radius bound is available and unavailable, respectively. For both algorithms, we prove the finite termination of the adapt"},"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":"2606.00517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2026-05-30T04:15:23Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"9953d836bb27330928e35ff0cef33566bb3f1d1a4cff05a74ac5a18a4d635638","abstract_canon_sha256":"7c3b7a968c04f66ecf7392aeb67e51b9e86fb51fa73931a8a097e551d87d8926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:57.054685Z","signature_b64":"+XgHuv5oLsJzY85gL44u5Hlknj4BNSpdPNcE3QDvd0BgbmBZF4Zpnso1jPqz+zR8zUZ1uBnaNqFuFaP/aIJtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"627c0c09d5497e3ccc531c6c5b795706fc148d4fad98c1a6ac1a76586fa5079a","last_reissued_at":"2026-06-02T01:03:57.053304Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:57.053304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep 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":"Lan Wang, Qiao Zhu, Ye Zhang","submitted_at":"2026-05-30T04:15:23Z","abstract_excerpt":"This paper studies the regularization of ill-posed inverse problems by deep neural networks (DNNs). We extend architecture-based regularization from shallow networks to deep models by developing a deterministic framework in which the admissible network class is enlarged adaptively and the resulting architecture complexity acts as the regularization mechanism. We propose two discrepancy-principle-driven expanding DNN algorithms to treat the cases where an explicit parameter-radius bound is available and unavailable, respectively. For both algorithms, we prove the finite termination of the adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00517","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/2606.00517/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":"2606.00517","created_at":"2026-06-02T01:03:57.054287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00517v1","created_at":"2026-06-02T01:03:57.054287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00517","created_at":"2026-06-02T01:03:57.054287+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJ6AYCOVJF7D","created_at":"2026-06-02T01:03:57.054287+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJ6AYCOVJF7DZTCT","created_at":"2026-06-02T01:03:57.054287+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJ6AYCOV","created_at":"2026-06-02T01:03:57.054287+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/MJ6AYCOVJF7DZTCTDRWFW6KXA3","json":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3.json","graph_json":"https://pith.science/api/pith-number/MJ6AYCOVJF7DZTCTDRWFW6KXA3/graph.json","events_json":"https://pith.science/api/pith-number/MJ6AYCOVJF7DZTCTDRWFW6KXA3/events.json","paper":"https://pith.science/paper/MJ6AYCOV"},"agent_actions":{"view_html":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3","download_json":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3.json","view_paper":"https://pith.science/paper/MJ6AYCOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00517&json=true","fetch_graph":"https://pith.science/api/pith-number/MJ6AYCOVJF7DZTCTDRWFW6KXA3/graph.json","fetch_events":"https://pith.science/api/pith-number/MJ6AYCOVJF7DZTCTDRWFW6KXA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3/action/storage_attestation","attest_author":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3/action/author_attestation","sign_citation":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3/action/citation_signature","submit_replication":"https://pith.science/pith/MJ6AYCOVJF7DZTCTDRWFW6KXA3/action/replication_record"}},"created_at":"2026-06-02T01:03:57.054287+00:00","updated_at":"2026-06-02T01:03:57.054287+00:00"}