{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EDN2KE2MKPPYTLXMGXB23CKL4O","short_pith_number":"pith:EDN2KE2M","canonical_record":{"source":{"id":"1812.03599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-10T02:41:06Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3013639bc997df735ffa14193dc5ef04cbf30d144914c6d9522307ce1a9322b8","abstract_canon_sha256":"df0501203b6c55559f8df16a2502e87f1c9bbc176331ee94429667ffe8d7c4d8"},"schema_version":"1.0"},"canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","source":{"kind":"arxiv","id":"1812.03599","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03599","created_at":"2026-05-17T23:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03599v2","created_at":"2026-05-17T23:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03599","created_at":"2026-05-17T23:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"EDN2KE2MKPPY","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EDN2KE2MKPPYTLXM","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EDN2KE2M","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EDN2KE2MKPPYTLXMGXB23CKL4O","target":"record","payload":{"canonical_record":{"source":{"id":"1812.03599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-10T02:41:06Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3013639bc997df735ffa14193dc5ef04cbf30d144914c6d9522307ce1a9322b8","abstract_canon_sha256":"df0501203b6c55559f8df16a2502e87f1c9bbc176331ee94429667ffe8d7c4d8"},"schema_version":"1.0"},"canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:09.233638Z","signature_b64":"q1Tu7GvU6PhNwQdGGd5CvXCH/wSpd47eO6Ntcae2unBQxU1SNlieWI3ZzHxzEzDsYC8LzN22VjzwRHMHEBglAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","last_reissued_at":"2026-05-17T23:43:09.233000Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:09.233000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.03599","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":"2026-05-17T23:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKnbTM+KzIAUz/hJBj6vqo7cfZpq9C/C0v3JIr4jtW05wufAfGEO3jJq1uhWpd2BCY3VhzF66dXfh0uqeAWfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T22:37:54.563029Z"},"content_sha256":"562b28ae685465090e30984dceac871ba401188b20c0c59b0f4e398c9069907e","schema_version":"1.0","event_id":"sha256:562b28ae685465090e30984dceac871ba401188b20c0c59b0f4e398c9069907e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EDN2KE2MKPPYTLXMGXB23CKL4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast convergence rates of deep neural networks for classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Ilsang Ohn, Yongdai Kim","submitted_at":"2018-12-10T02:41:06Z","abstract_excerpt":"We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast rate convergences for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity). is carefully "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03599","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":"2026-05-17T23:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"clWJW42e95/9GsskC0YI+xD46h64g9LX2ULhP9xl7dMPhcYkcT9ptvryqXGykoES7E0qUEuWTTuiTr2DluCmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T22:37:54.563378Z"},"content_sha256":"4966e6c277f205c761438fb62d72a3cc16e6a34a10fda7376556dca518178777","schema_version":"1.0","event_id":"sha256:4966e6c277f205c761438fb62d72a3cc16e6a34a10fda7376556dca518178777"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/bundle.json","state_url":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/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":"2026-06-08T22:37:54Z","links":{"resolver":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O","bundle":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/bundle.json","state":"https://pith.science/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDN2KE2MKPPYTLXMGXB23CKL4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EDN2KE2MKPPYTLXMGXB23CKL4O","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":"df0501203b6c55559f8df16a2502e87f1c9bbc176331ee94429667ffe8d7c4d8","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-10T02:41:06Z","title_canon_sha256":"3013639bc997df735ffa14193dc5ef04cbf30d144914c6d9522307ce1a9322b8"},"schema_version":"1.0","source":{"id":"1812.03599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03599","created_at":"2026-05-17T23:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03599v2","created_at":"2026-05-17T23:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03599","created_at":"2026-05-17T23:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"EDN2KE2MKPPY","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EDN2KE2MKPPYTLXM","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EDN2KE2M","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:4966e6c277f205c761438fb62d72a3cc16e6a34a10fda7376556dca518178777","target":"graph","created_at":"2026-05-17T23:43:09Z","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 derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast rate convergences for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity). is carefully ","authors_text":"Dongha Kim, Ilsang Ohn, Yongdai Kim","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-10T02:41:06Z","title":"Fast convergence rates of deep neural networks for classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03599","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":"sha256:562b28ae685465090e30984dceac871ba401188b20c0c59b0f4e398c9069907e","target":"record","created_at":"2026-05-17T23:43:09Z","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":"df0501203b6c55559f8df16a2502e87f1c9bbc176331ee94429667ffe8d7c4d8","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-10T02:41:06Z","title_canon_sha256":"3013639bc997df735ffa14193dc5ef04cbf30d144914c6d9522307ce1a9322b8"},"schema_version":"1.0","source":{"id":"1812.03599","kind":"arxiv","version":2}},"canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20dba5134c53df89aeec35c3ad894be3855ef5b0d1aa9238f62c5a48a944d2ef","first_computed_at":"2026-05-17T23:43:09.233000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:09.233000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q1Tu7GvU6PhNwQdGGd5CvXCH/wSpd47eO6Ntcae2unBQxU1SNlieWI3ZzHxzEzDsYC8LzN22VjzwRHMHEBglAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:09.233638Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.03599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:562b28ae685465090e30984dceac871ba401188b20c0c59b0f4e398c9069907e","sha256:4966e6c277f205c761438fb62d72a3cc16e6a34a10fda7376556dca518178777"],"state_sha256":"981c791bb15c2009ce3ab37eb9f57763beeb31ad60cb8ddde1e46f2d11ec441e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aGuTBttpmjIAEUvQOGJ0MYi4pMZJnmqfiRcYwYYxq9Z2c7LTN3Z4JIArk+3ebR86aysqjHs0Vqlp1Jo84x4nDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T22:37:54.565212Z","bundle_sha256":"0a3cea3aa4d25b13cb47ad129485b98a88b5a2dc460d6022cbf5457449e93e8f"}}