{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RWXKL7FZEOJUG3LJEK2HNTHPBW","short_pith_number":"pith:RWXKL7FZ","canonical_record":{"source":{"id":"1905.02199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T12:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"f2579d39ff48da3e836ae871029959430970b41f3f797f36493bca48a61a997e","abstract_canon_sha256":"9958d75122d214dc9a9190331f6557aed370aca6749cfbada009f879f4173753"},"schema_version":"1.0"},"canonical_sha256":"8daea5fcb92393436d6922b476ccef0d9867104bc496c17182086b142b1736f3","source":{"kind":"arxiv","id":"1905.02199","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02199","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02199v1","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02199","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"RWXKL7FZEOJU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RWXKL7FZEOJUG3LJ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RWXKL7FZ","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RWXKL7FZEOJUG3LJEK2HNTHPBW","target":"record","payload":{"canonical_record":{"source":{"id":"1905.02199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T12:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"f2579d39ff48da3e836ae871029959430970b41f3f797f36493bca48a61a997e","abstract_canon_sha256":"9958d75122d214dc9a9190331f6557aed370aca6749cfbada009f879f4173753"},"schema_version":"1.0"},"canonical_sha256":"8daea5fcb92393436d6922b476ccef0d9867104bc496c17182086b142b1736f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:52.041996Z","signature_b64":"nTVSVmXx3xga8CMieI1hid42aNhCd8h0SqNqwgHhLGwsGZq9FVcQQHn9PbuYolQFEqPF9+L/kWLYpTacZdjtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8daea5fcb92393436d6922b476ccef0d9867104bc496c17182086b142b1736f3","last_reissued_at":"2026-05-17T23:46:52.041343Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:52.041343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.02199","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nI/AfeqDCyrDqw8i/k6rsS1gR8TGpAsJXBA4kmyv50auibre4xjG4a3gNsSOtwYIul91KbJnO6gLK7OQ25qMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:11:26.001945Z"},"content_sha256":"385faa69049adb36caab7b8275a69188d1a97cf989a451dfef44d718c53745c1","schema_version":"1.0","event_id":"sha256:385faa69049adb36caab7b8275a69188d1a97cf989a451dfef44d718c53745c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RWXKL7FZEOJUG3LJEK2HNTHPBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nonlinear Approximation and (Deep) ReLU Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"B. Hanin, G. Petrova, I. Daubechies, R. DeVore, S. Foucart","submitted_at":"2019-05-05T12:54:35Z","abstract_excerpt":"This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural networks approximate functions with classical smoothness to the same accuracy as classical linear methods of approximation, e.g. approximation by polynomials or by piecewise polynomials on prescribed partitions. However, approximation by neural networks depending on n parameters is a form of nonlinear approximation and as such should be compared with other "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02199","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"106u7sALL1USijMFRpbTjCAqcTStXhCVrO9xIc3quRTuEn1FeUveP+AQHvj+wSTOZQaIILvfeL1mccm1GBNQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:11:26.002286Z"},"content_sha256":"1cff06df0f0b4c23bfa0949e3af1a9c1bd3104457c0d4e88fff4f942a656762b","schema_version":"1.0","event_id":"sha256:1cff06df0f0b4c23bfa0949e3af1a9c1bd3104457c0d4e88fff4f942a656762b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW/bundle.json","state_url":"https://pith.science/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T12:11:26Z","links":{"resolver":"https://pith.science/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW","bundle":"https://pith.science/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW/bundle.json","state":"https://pith.science/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWXKL7FZEOJUG3LJEK2HNTHPBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RWXKL7FZEOJUG3LJEK2HNTHPBW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9958d75122d214dc9a9190331f6557aed370aca6749cfbada009f879f4173753","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T12:54:35Z","title_canon_sha256":"f2579d39ff48da3e836ae871029959430970b41f3f797f36493bca48a61a997e"},"schema_version":"1.0","source":{"id":"1905.02199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02199","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02199v1","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02199","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"RWXKL7FZEOJU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RWXKL7FZEOJUG3LJ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RWXKL7FZ","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:1cff06df0f0b4c23bfa0949e3af1a9c1bd3104457c0d4e88fff4f942a656762b","target":"graph","created_at":"2026-05-17T23:46:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural networks approximate functions with classical smoothness to the same accuracy as classical linear methods of approximation, e.g. approximation by polynomials or by piecewise polynomials on prescribed partitions. However, approximation by neural networks depending on n parameters is a form of nonlinear approximation and as such should be compared with other ","authors_text":"B. Hanin, G. Petrova, I. Daubechies, R. DeVore, S. Foucart","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T12:54:35Z","title":"Nonlinear Approximation and (Deep) ReLU Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02199","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:385faa69049adb36caab7b8275a69188d1a97cf989a451dfef44d718c53745c1","target":"record","created_at":"2026-05-17T23:46:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9958d75122d214dc9a9190331f6557aed370aca6749cfbada009f879f4173753","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T12:54:35Z","title_canon_sha256":"f2579d39ff48da3e836ae871029959430970b41f3f797f36493bca48a61a997e"},"schema_version":"1.0","source":{"id":"1905.02199","kind":"arxiv","version":1}},"canonical_sha256":"8daea5fcb92393436d6922b476ccef0d9867104bc496c17182086b142b1736f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8daea5fcb92393436d6922b476ccef0d9867104bc496c17182086b142b1736f3","first_computed_at":"2026-05-17T23:46:52.041343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:52.041343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nTVSVmXx3xga8CMieI1hid42aNhCd8h0SqNqwgHhLGwsGZq9FVcQQHn9PbuYolQFEqPF9+L/kWLYpTacZdjtBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:52.041996Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.02199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:385faa69049adb36caab7b8275a69188d1a97cf989a451dfef44d718c53745c1","sha256:1cff06df0f0b4c23bfa0949e3af1a9c1bd3104457c0d4e88fff4f942a656762b"],"state_sha256":"5ddb90bc82e1d2e5ab61abbacea75198c7d4e0734b521092602e9eaaee169ec3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEDfB4lAaqoIrBT0MqwQxNDWSJaR6+wudeVBLYQx0MdjdbfGn51IVeq3KHrNR8Ta8vegtoBLhHTww3KQmD8dCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:11:26.004237Z","bundle_sha256":"1f3caeb1b6f40ec21504e33e8bb370abf9a829cc81ed40dec5f98403928879cf"}}