{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:V7VY7RA5GCCKD66H7DTAZ2P3VA","short_pith_number":"pith:V7VY7RA5","canonical_record":{"source":{"id":"1802.04474","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T06:24:27Z","cross_cats_sorted":[],"title_canon_sha256":"dd01eac680c3991e425780fae192a5bda2867097135cb38264f65033bbb01aff","abstract_canon_sha256":"6d315dc49d4329822d2d0562eb112b31dfcbacb68eeb9c4488970f3fbcc7d3d1"},"schema_version":"1.0"},"canonical_sha256":"afeb8fc41d3084a1fbc7f8e60ce9fba81cab25f7015e08746699dcf1c478c3fa","source":{"kind":"arxiv","id":"1802.04474","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04474","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04474v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04474","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"V7VY7RA5GCCK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V7VY7RA5GCCKD66H","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V7VY7RA5","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:V7VY7RA5GCCKD66H7DTAZ2P3VA","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04474","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T06:24:27Z","cross_cats_sorted":[],"title_canon_sha256":"dd01eac680c3991e425780fae192a5bda2867097135cb38264f65033bbb01aff","abstract_canon_sha256":"6d315dc49d4329822d2d0562eb112b31dfcbacb68eeb9c4488970f3fbcc7d3d1"},"schema_version":"1.0"},"canonical_sha256":"afeb8fc41d3084a1fbc7f8e60ce9fba81cab25f7015e08746699dcf1c478c3fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:17.918943Z","signature_b64":"hzu2PtkG88pk4UY/TrmUDgRdavNmgVdBCQtOn4BtrOnVg/MrH5qf9NFHb+5tF+6qUWJfXG6zw5Awf5t0Ap68AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afeb8fc41d3084a1fbc7f8e60ce9fba81cab25f7015e08746699dcf1c478c3fa","last_reissued_at":"2026-05-18T00:11:17.918257Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:17.918257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04474","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIak0L6KEsgZouNg7nmrGZASgduqVVzWcRbwIAfQvmmmGnkyynb3vPA0M3/1STk9cgDesYzNmdw53wuuP0JeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:32:20.811109Z"},"content_sha256":"36450e138560c80ea0881cafc034ca713fad68e38c388f7ed94d02649874d251","schema_version":"1.0","event_id":"sha256:36450e138560c80ea0881cafc034ca713fad68e38c388f7ed94d02649874d251"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:V7VY7RA5GCCKD66H7DTAZ2P3VA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Neural Networks Learn Non-Smooth Functions Effectively","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Kenji Fukumizu, Masaaki Imaizumi","submitted_at":"2018-02-13T06:24:27Z","abstract_excerpt":"We theoretically discuss why deep neural networks (DNNs) performs better than other models in some cases by investigating statistical properties of DNNs for non-smooth functions. While DNNs have empirically shown higher performance than other standard methods, understanding its mechanism is still a challenging problem. From an aspect of the statistical theory, it is known many standard methods attain the optimal rate of generalization errors for smooth functions in large sample asymptotics, and thus it has not been straightforward to find theoretical advantages of DNNs. This paper fills this g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04474","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":""},"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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neXiUTOSSayoYC/WctMKcueW/gtBYKJe5AfYagoTbkSetfLfWQa3AIgHsR3haQtT8Mq++mC/ErAeKhdu7MSBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:32:20.811458Z"},"content_sha256":"53717c350cbfc4936c7a18c92a2850111757522b25dd72f2b470ac8eb01afab1","schema_version":"1.0","event_id":"sha256:53717c350cbfc4936c7a18c92a2850111757522b25dd72f2b470ac8eb01afab1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA/bundle.json","state_url":"https://pith.science/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA/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":"2026-07-04T18:32:20Z","links":{"resolver":"https://pith.science/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA","bundle":"https://pith.science/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA/bundle.json","state":"https://pith.science/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7VY7RA5GCCKD66H7DTAZ2P3VA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:V7VY7RA5GCCKD66H7DTAZ2P3VA","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":"6d315dc49d4329822d2d0562eb112b31dfcbacb68eeb9c4488970f3fbcc7d3d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T06:24:27Z","title_canon_sha256":"dd01eac680c3991e425780fae192a5bda2867097135cb38264f65033bbb01aff"},"schema_version":"1.0","source":{"id":"1802.04474","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04474","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04474v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04474","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"V7VY7RA5GCCK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V7VY7RA5GCCKD66H","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V7VY7RA5","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:53717c350cbfc4936c7a18c92a2850111757522b25dd72f2b470ac8eb01afab1","target":"graph","created_at":"2026-05-18T00:11:17Z","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":"We theoretically discuss why deep neural networks (DNNs) performs better than other models in some cases by investigating statistical properties of DNNs for non-smooth functions. While DNNs have empirically shown higher performance than other standard methods, understanding its mechanism is still a challenging problem. From an aspect of the statistical theory, it is known many standard methods attain the optimal rate of generalization errors for smooth functions in large sample asymptotics, and thus it has not been straightforward to find theoretical advantages of DNNs. This paper fills this g","authors_text":"Kenji Fukumizu, Masaaki Imaizumi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T06:24:27Z","title":"Deep Neural Networks Learn Non-Smooth Functions Effectively"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04474","kind":"arxiv","version":2},"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":"sha256:36450e138560c80ea0881cafc034ca713fad68e38c388f7ed94d02649874d251","target":"record","created_at":"2026-05-18T00:11:17Z","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":"6d315dc49d4329822d2d0562eb112b31dfcbacb68eeb9c4488970f3fbcc7d3d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T06:24:27Z","title_canon_sha256":"dd01eac680c3991e425780fae192a5bda2867097135cb38264f65033bbb01aff"},"schema_version":"1.0","source":{"id":"1802.04474","kind":"arxiv","version":2}},"canonical_sha256":"afeb8fc41d3084a1fbc7f8e60ce9fba81cab25f7015e08746699dcf1c478c3fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afeb8fc41d3084a1fbc7f8e60ce9fba81cab25f7015e08746699dcf1c478c3fa","first_computed_at":"2026-05-18T00:11:17.918257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:17.918257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hzu2PtkG88pk4UY/TrmUDgRdavNmgVdBCQtOn4BtrOnVg/MrH5qf9NFHb+5tF+6qUWJfXG6zw5Awf5t0Ap68AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:17.918943Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04474","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36450e138560c80ea0881cafc034ca713fad68e38c388f7ed94d02649874d251","sha256:53717c350cbfc4936c7a18c92a2850111757522b25dd72f2b470ac8eb01afab1"],"state_sha256":"7f9bc7baa201fcd5d17e9b80c125c2bcddeec70ccabcf365947f8424a7b7bf85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBjYs4NL5NMPlrslsGN0dV0JQm2lLwZ4qbWLTm8ydTqvDBDeBd/7QMWAwRSwR9hgwVx8Jv8ZDTM4bS+mSmpcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:32:20.813655Z","bundle_sha256":"889a31ded23c583af0dc818cd9e6c59f24291bdd1eff336dd499775e9f1b69bb"}}