{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VAQBQ27CVY7OOI5ACA4DQ6M7LN","short_pith_number":"pith:VAQBQ27C","schema_version":"1.0","canonical_sha256":"a820186be2ae3ee723a0103838799f5b632f81b522375ac19e02f033b8b55a6f","source":{"kind":"arxiv","id":"2011.09363","version":2},"attestation_state":"computed","paper":{"title":"Neural network approximation and estimation of classifiers with classification boundary in a Barron class","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.FA","authors_text":"Andrei Caragea, Felix Voigtlaender, Philipp Petersen","submitted_at":"2020-11-18T16:00:31Z","abstract_excerpt":"We prove bounds for the approximation and estimation of certain binary classification functions using ReLU neural networks. Our estimation bounds provide a priori performance guarantees for empirical risk minimization using networks of a suitable size, depending on the number of training samples available. The obtained approximation and estimation rates are independent of the dimension of the input, showing that the curse of dimensionality can be overcome in this setting; in fact, the input dimension only enters in the form of a polynomial factor. Regarding the regularity of the target classif"},"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":"2011.09363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.FA","submitted_at":"2020-11-18T16:00:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9c46c0653c71496ebba9201ff6e873bb94aba9060eb51e2398eac51080ff5da3","abstract_canon_sha256":"fc461bc5ab11c5992126cbbc25fe4412d44662d84285bee7c45deaf1a1c6f61e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:35.934497Z","signature_b64":"bLbxQ01AYC6OV/YDaEPEzxP+yEmsNSZ2jgzIQCpDcCsdNJZF5SU/1Gur3Zls/WslGCTueDjKGnFmpNDOPvs2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a820186be2ae3ee723a0103838799f5b632f81b522375ac19e02f033b8b55a6f","last_reissued_at":"2026-07-05T04:03:35.933906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:35.933906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural network approximation and estimation of classifiers with classification boundary in a Barron class","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.FA","authors_text":"Andrei Caragea, Felix Voigtlaender, Philipp Petersen","submitted_at":"2020-11-18T16:00:31Z","abstract_excerpt":"We prove bounds for the approximation and estimation of certain binary classification functions using ReLU neural networks. Our estimation bounds provide a priori performance guarantees for empirical risk minimization using networks of a suitable size, depending on the number of training samples available. The obtained approximation and estimation rates are independent of the dimension of the input, showing that the curse of dimensionality can be overcome in this setting; in fact, the input dimension only enters in the form of a polynomial factor. Regarding the regularity of the target classif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09363","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/2011.09363/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":"2011.09363","created_at":"2026-07-05T04:03:35.933983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.09363v2","created_at":"2026-07-05T04:03:35.933983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09363","created_at":"2026-07-05T04:03:35.933983+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAQBQ27CVY7O","created_at":"2026-07-05T04:03:35.933983+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAQBQ27CVY7OOI5A","created_at":"2026-07-05T04:03:35.933983+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAQBQ27C","created_at":"2026-07-05T04:03:35.933983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2112.14523","citing_title":"Deep neural network approximation theory for high-dimensional functions","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN","json":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN.json","graph_json":"https://pith.science/api/pith-number/VAQBQ27CVY7OOI5ACA4DQ6M7LN/graph.json","events_json":"https://pith.science/api/pith-number/VAQBQ27CVY7OOI5ACA4DQ6M7LN/events.json","paper":"https://pith.science/paper/VAQBQ27C"},"agent_actions":{"view_html":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN","download_json":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN.json","view_paper":"https://pith.science/paper/VAQBQ27C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.09363&json=true","fetch_graph":"https://pith.science/api/pith-number/VAQBQ27CVY7OOI5ACA4DQ6M7LN/graph.json","fetch_events":"https://pith.science/api/pith-number/VAQBQ27CVY7OOI5ACA4DQ6M7LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN/action/storage_attestation","attest_author":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN/action/author_attestation","sign_citation":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN/action/citation_signature","submit_replication":"https://pith.science/pith/VAQBQ27CVY7OOI5ACA4DQ6M7LN/action/replication_record"}},"created_at":"2026-07-05T04:03:35.933983+00:00","updated_at":"2026-07-05T04:03:35.933983+00:00"}