{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UFRLROJMXY7LWYBU32466EME4W","short_pith_number":"pith:UFRLROJM","schema_version":"1.0","canonical_sha256":"a162b8b92cbe3ebb6034deb9ef1184e5963865a1f2be6c5c47ad13c091818bff","source":{"kind":"arxiv","id":"2503.01860","version":1},"attestation_state":"computed","paper":{"title":"Nonsmooth Optimisation and neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Nadezda Sukhorukova, Vinesha Peiris","submitted_at":"2025-02-24T04:06:27Z","abstract_excerpt":"In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approximation by a neural network without hidden layers, the activation functions are restricted to continuous strictly increasing functions. We develop an algorithm for computing the approximation with one hidden layer through a step-by-step procedure. The nonsmooth analysis techniques demonstrated their efficiency. In particular, they partially explain why the developed step-by-step procedure may run without any objective f"},"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":"2503.01860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-24T04:06:27Z","cross_cats_sorted":[],"title_canon_sha256":"3ceda803dabe9377e5476846e6f16e1e6671be689c51e3a9b36ee2119b73978e","abstract_canon_sha256":"28f67b22536d7d0a5e517e2aa37adbd8357204f33440c0773fd6f2f55aab827f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:31.281501Z","signature_b64":"Gd1lh2nF0t8u8CR7zNsq/bH758VdmTmK7WCXDsx9VJysnyngPAQWtTlXxVL1xWy8IgJgCzKzG43k4XkVvQsDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a162b8b92cbe3ebb6034deb9ef1184e5963865a1f2be6c5c47ad13c091818bff","last_reissued_at":"2026-07-05T10:23:31.280933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:31.280933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonsmooth Optimisation and neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Nadezda Sukhorukova, Vinesha Peiris","submitted_at":"2025-02-24T04:06:27Z","abstract_excerpt":"In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approximation by a neural network without hidden layers, the activation functions are restricted to continuous strictly increasing functions. We develop an algorithm for computing the approximation with one hidden layer through a step-by-step procedure. The nonsmooth analysis techniques demonstrated their efficiency. In particular, they partially explain why the developed step-by-step procedure may run without any objective f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01860","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/2503.01860/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":"2503.01860","created_at":"2026-07-05T10:23:31.281016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01860v1","created_at":"2026-07-05T10:23:31.281016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01860","created_at":"2026-07-05T10:23:31.281016+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFRLROJMXY7L","created_at":"2026-07-05T10:23:31.281016+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFRLROJMXY7LWYBU","created_at":"2026-07-05T10:23:31.281016+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFRLROJM","created_at":"2026-07-05T10:23:31.281016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17305","citing_title":"KKT-based optimality conditions for neural network approximation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W","json":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W.json","graph_json":"https://pith.science/api/pith-number/UFRLROJMXY7LWYBU32466EME4W/graph.json","events_json":"https://pith.science/api/pith-number/UFRLROJMXY7LWYBU32466EME4W/events.json","paper":"https://pith.science/paper/UFRLROJM"},"agent_actions":{"view_html":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W","download_json":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W.json","view_paper":"https://pith.science/paper/UFRLROJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01860&json=true","fetch_graph":"https://pith.science/api/pith-number/UFRLROJMXY7LWYBU32466EME4W/graph.json","fetch_events":"https://pith.science/api/pith-number/UFRLROJMXY7LWYBU32466EME4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W/action/storage_attestation","attest_author":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W/action/author_attestation","sign_citation":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W/action/citation_signature","submit_replication":"https://pith.science/pith/UFRLROJMXY7LWYBU32466EME4W/action/replication_record"}},"created_at":"2026-07-05T10:23:31.281016+00:00","updated_at":"2026-07-05T10:23:31.281016+00:00"}