{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3UI4ZG3KWYOXFE3Q5RD5MA2DGN","short_pith_number":"pith:3UI4ZG3K","schema_version":"1.0","canonical_sha256":"dd11cc9b6ab61d729370ec47d60343337cff9cbd01c01d6b0b83068f07baef23","source":{"kind":"arxiv","id":"1905.01208","version":4},"attestation_state":"computed","paper":{"title":"Approximation spaces of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"math.FA","authors_text":"DANTE), Felix Voigtlaender (KU), Gitta Kutyniok, Morten Nielsen, R\\'emi Gribonval (PANAMA","submitted_at":"2019-05-03T14:43:23Z","abstract_excerpt":"We study the expressivity of deep neural networks. Measuring a network's complexity by its number of connections or by its number of neurons, we consider the class of functions for which the error of best approximation with networks of a given complexity decays at a certain rate when increasing the complexity budget. Using results from classical approximation theory, we show that this class can be endowed with a (quasi)-norm that makes it a linear function space, called approximation space. We establish that allowing the networks to have certain types of \"skip connections\" does not change the "},"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":"1905.01208","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.FA","submitted_at":"2019-05-03T14:43:23Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"54c873835dfdc68d532aaa9a5f55bdfe1ef2949fbf6cedf29bf47f384cfc35f8","abstract_canon_sha256":"89b3b2d44569d5db91751e372b690e15a784a1acaee4daaf7d71b4e303949239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:04.561830Z","signature_b64":"pQr5gj58OQevL4+l4fFTpEBm+BmIxXoUczJXCjQ1ooMWexsZwgYRIpYOCcm1VrhToxj3yT7uWWU8bhJOFzIcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd11cc9b6ab61d729370ec47d60343337cff9cbd01c01d6b0b83068f07baef23","last_reissued_at":"2026-07-05T01:20:04.561288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:04.561288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation spaces of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"math.FA","authors_text":"DANTE), Felix Voigtlaender (KU), Gitta Kutyniok, Morten Nielsen, R\\'emi Gribonval (PANAMA","submitted_at":"2019-05-03T14:43:23Z","abstract_excerpt":"We study the expressivity of deep neural networks. Measuring a network's complexity by its number of connections or by its number of neurons, we consider the class of functions for which the error of best approximation with networks of a given complexity decays at a certain rate when increasing the complexity budget. Using results from classical approximation theory, we show that this class can be endowed with a (quasi)-norm that makes it a linear function space, called approximation space. We establish that allowing the networks to have certain types of \"skip connections\" does not change the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01208","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/1905.01208/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":"1905.01208","created_at":"2026-07-05T01:20:04.561359+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.01208v4","created_at":"2026-07-05T01:20:04.561359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01208","created_at":"2026-07-05T01:20:04.561359+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UI4ZG3KWYOX","created_at":"2026-07-05T01:20:04.561359+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UI4ZG3KWYOXFE3Q","created_at":"2026-07-05T01:20:04.561359+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UI4ZG3K","created_at":"2026-07-05T01:20:04.561359+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":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN","json":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN.json","graph_json":"https://pith.science/api/pith-number/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/graph.json","events_json":"https://pith.science/api/pith-number/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/events.json","paper":"https://pith.science/paper/3UI4ZG3K"},"agent_actions":{"view_html":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN","download_json":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN.json","view_paper":"https://pith.science/paper/3UI4ZG3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.01208&json=true","fetch_graph":"https://pith.science/api/pith-number/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/graph.json","fetch_events":"https://pith.science/api/pith-number/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/action/storage_attestation","attest_author":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/action/author_attestation","sign_citation":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/action/citation_signature","submit_replication":"https://pith.science/pith/3UI4ZG3KWYOXFE3Q5RD5MA2DGN/action/replication_record"}},"created_at":"2026-07-05T01:20:04.561359+00:00","updated_at":"2026-07-05T01:20:04.561359+00:00"}