{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BXBOTZGUEMJJA7WT7SNJACOVEI","short_pith_number":"pith:BXBOTZGU","schema_version":"1.0","canonical_sha256":"0dc2e9e4d42312907ed3fc9a9009d522296d191934eae98e6e6962d495d13920","source":{"kind":"arxiv","id":"2410.14759","version":4},"attestation_state":"computed","paper":{"title":"Universal approximation results for neural networks with non-polynomial activation function over non-compact domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.CA"],"primary_cat":"stat.ML","authors_text":"Ariel Neufeld, Philipp Schmocker","submitted_at":"2024-10-18T09:53:20Z","abstract_excerpt":"This paper extends the universal approximation property of single-hidden-layer feedforward neural networks beyond compact domains, which is of particular interest for the approximation within weighted $C^k$-spaces and weighted Sobolev spaces over unbounded domains. More precisely, by assuming that the activation function is non-polynomial, we establish universal approximation results within function spaces defined over non-compact subsets of a Euclidean space, including $L^p$-spaces, weighted $C^k$-spaces, and weighted Sobolev spaces, where the latter two include the approximation of the (weak"},"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":"2410.14759","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-18T09:53:20Z","cross_cats_sorted":["cs.LG","cs.NE","math.CA"],"title_canon_sha256":"29324af3a7aa4c9931c479b67364335d419da95c42db92f7b3fccf487fa26dbe","abstract_canon_sha256":"c781b220dae6c9c848dfb81eddea5c5ec1595183c5dba0e4b3ac544bb1fae9f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:20.207655Z","signature_b64":"zV7s75BA54il8eTDfEOISh7DtlPrZzimPGDAploAUcuhWlWq2Fr3fVKw+6W3qTahj5S+TYEdEGzyCtsHjA6AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc2e9e4d42312907ed3fc9a9009d522296d191934eae98e6e6962d495d13920","last_reissued_at":"2026-07-05T11:32:20.207129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:20.207129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal approximation results for neural networks with non-polynomial activation function over non-compact domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.CA"],"primary_cat":"stat.ML","authors_text":"Ariel Neufeld, Philipp Schmocker","submitted_at":"2024-10-18T09:53:20Z","abstract_excerpt":"This paper extends the universal approximation property of single-hidden-layer feedforward neural networks beyond compact domains, which is of particular interest for the approximation within weighted $C^k$-spaces and weighted Sobolev spaces over unbounded domains. More precisely, by assuming that the activation function is non-polynomial, we establish universal approximation results within function spaces defined over non-compact subsets of a Euclidean space, including $L^p$-spaces, weighted $C^k$-spaces, and weighted Sobolev spaces, where the latter two include the approximation of the (weak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14759","kind":"arxiv","version":4},"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/2410.14759/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":"2410.14759","created_at":"2026-07-05T11:32:20.207192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14759v4","created_at":"2026-07-05T11:32:20.207192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14759","created_at":"2026-07-05T11:32:20.207192+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXBOTZGUEMJJ","created_at":"2026-07-05T11:32:20.207192+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXBOTZGUEMJJA7WT","created_at":"2026-07-05T11:32:20.207192+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXBOTZGU","created_at":"2026-07-05T11:32:20.207192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23156","citing_title":"Any-Dimensional Invariant Universality","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2312.08410","citing_title":"Universal approximation property of Banach space-valued random feature models including random neural networks","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI","json":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI.json","graph_json":"https://pith.science/api/pith-number/BXBOTZGUEMJJA7WT7SNJACOVEI/graph.json","events_json":"https://pith.science/api/pith-number/BXBOTZGUEMJJA7WT7SNJACOVEI/events.json","paper":"https://pith.science/paper/BXBOTZGU"},"agent_actions":{"view_html":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI","download_json":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI.json","view_paper":"https://pith.science/paper/BXBOTZGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14759&json=true","fetch_graph":"https://pith.science/api/pith-number/BXBOTZGUEMJJA7WT7SNJACOVEI/graph.json","fetch_events":"https://pith.science/api/pith-number/BXBOTZGUEMJJA7WT7SNJACOVEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI/action/storage_attestation","attest_author":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI/action/author_attestation","sign_citation":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI/action/citation_signature","submit_replication":"https://pith.science/pith/BXBOTZGUEMJJA7WT7SNJACOVEI/action/replication_record"}},"created_at":"2026-07-05T11:32:20.207192+00:00","updated_at":"2026-07-05T11:32:20.207192+00:00"}