{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:AFU4FRKAOJJZ6HIK3DXDNFF5MB","short_pith_number":"pith:AFU4FRKA","canonical_record":{"source":{"id":"1402.3811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-02-16T15:54:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"68fc45e464cde12b3c18d2f5afb95a45d513a393198352dfd783cfe335eec0a6","abstract_canon_sha256":"17c4af161fcc5da20bc25a89ab576e300db4489090394bd59bc431bfbae6a83e"},"schema_version":"1.0"},"canonical_sha256":"0169c2c54072539f1d0ad8ee3694bd6079a52a92ac4b2e2c11db8acd98fd4007","source":{"kind":"arxiv","id":"1402.3811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.3811","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"1402.3811v2","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.3811","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"AFU4FRKAOJJZ","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"AFU4FRKAOJJZ6HIK","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"AFU4FRKA","created_at":"2026-07-05T01:16:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:AFU4FRKAOJJZ6HIK3DXDNFF5MB","target":"record","payload":{"canonical_record":{"source":{"id":"1402.3811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-02-16T15:54:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"68fc45e464cde12b3c18d2f5afb95a45d513a393198352dfd783cfe335eec0a6","abstract_canon_sha256":"17c4af161fcc5da20bc25a89ab576e300db4489090394bd59bc431bfbae6a83e"},"schema_version":"1.0"},"canonical_sha256":"0169c2c54072539f1d0ad8ee3694bd6079a52a92ac4b2e2c11db8acd98fd4007","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:30.362746Z","signature_b64":"CGXuSR7Jwy0zhU2JJVI5qIuvSZfQuqiDTQ5WqvSvpKvTMMUPpJQwmWcZBLcr5nsWvqRJgqW06x5IPRVjQ6cAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0169c2c54072539f1d0ad8ee3694bd6079a52a92ac4b2e2c11db8acd98fd4007","last_reissued_at":"2026-07-05T01:16:30.362243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:30.362243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.3811","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":"2026-07-05T01:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vl73YUv6jn4Y7OJp8dNWfIHPzofH/NSCwStQ+XHb4eXzx7dY6UtRk6TVhTwsZSdFxnACmHFiNwEK25NiGZ9gDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:36:26.962959Z"},"content_sha256":"8e2d43b7807bfcd684083493e0f8c91613805433d0077662098a18d07e14bbbb","schema_version":"1.0","event_id":"sha256:8e2d43b7807bfcd684083493e0f8c91613805433d0077662098a18d07e14bbbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:AFU4FRKAOJJZ6HIK3DXDNFF5MB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout Rademacher Complexity of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.NE","authors_text":"Wei Gao, Zhi-Hua Zhou","submitted_at":"2014-02-16T15:54:37Z","abstract_excerpt":"Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper, we study the Rademacher complexity of different types of dropout, and our theoretical results disclose that for shallow neural networks (with one or none hidden layer) dropout"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.3811","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/1402.3811/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BB0/PHHfQboHIQ35nUo1Mu3Il7lSxlyBtlQ+ztm547S3oeD6zvI6+gCXn1Iop2osp3sD2tcZIZMQZxGcElS4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:36:26.963368Z"},"content_sha256":"ec3c62f41bb63d2a530a74083b6aae1257fadeec0746d63562a65f90d440d906","schema_version":"1.0","event_id":"sha256:ec3c62f41bb63d2a530a74083b6aae1257fadeec0746d63562a65f90d440d906"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB/bundle.json","state_url":"https://pith.science/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB/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":"2026-08-07T12:36:26Z","links":{"resolver":"https://pith.science/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB","bundle":"https://pith.science/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB/bundle.json","state":"https://pith.science/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AFU4FRKAOJJZ6HIK3DXDNFF5MB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:AFU4FRKAOJJZ6HIK3DXDNFF5MB","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":"17c4af161fcc5da20bc25a89ab576e300db4489090394bd59bc431bfbae6a83e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-02-16T15:54:37Z","title_canon_sha256":"68fc45e464cde12b3c18d2f5afb95a45d513a393198352dfd783cfe335eec0a6"},"schema_version":"1.0","source":{"id":"1402.3811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.3811","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"1402.3811v2","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.3811","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"AFU4FRKAOJJZ","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"AFU4FRKAOJJZ6HIK","created_at":"2026-07-05T01:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"AFU4FRKA","created_at":"2026-07-05T01:16:30Z"}],"graph_snapshots":[{"event_id":"sha256:ec3c62f41bb63d2a530a74083b6aae1257fadeec0746d63562a65f90d440d906","target":"graph","created_at":"2026-07-05T01:16:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1402.3811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper, we study the Rademacher complexity of different types of dropout, and our theoretical results disclose that for shallow neural networks (with one or none hidden layer) dropout","authors_text":"Wei Gao, Zhi-Hua Zhou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-02-16T15:54:37Z","title":"Dropout Rademacher Complexity of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.3811","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":"sha256:8e2d43b7807bfcd684083493e0f8c91613805433d0077662098a18d07e14bbbb","target":"record","created_at":"2026-07-05T01:16:30Z","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":"17c4af161fcc5da20bc25a89ab576e300db4489090394bd59bc431bfbae6a83e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-02-16T15:54:37Z","title_canon_sha256":"68fc45e464cde12b3c18d2f5afb95a45d513a393198352dfd783cfe335eec0a6"},"schema_version":"1.0","source":{"id":"1402.3811","kind":"arxiv","version":2}},"canonical_sha256":"0169c2c54072539f1d0ad8ee3694bd6079a52a92ac4b2e2c11db8acd98fd4007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0169c2c54072539f1d0ad8ee3694bd6079a52a92ac4b2e2c11db8acd98fd4007","first_computed_at":"2026-07-05T01:16:30.362243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:30.362243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CGXuSR7Jwy0zhU2JJVI5qIuvSZfQuqiDTQ5WqvSvpKvTMMUPpJQwmWcZBLcr5nsWvqRJgqW06x5IPRVjQ6cAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:30.362746Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.3811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e2d43b7807bfcd684083493e0f8c91613805433d0077662098a18d07e14bbbb","sha256:ec3c62f41bb63d2a530a74083b6aae1257fadeec0746d63562a65f90d440d906"],"state_sha256":"da794222dffd86599001636ec575e9681417c962628b71719b86ac24e4481586"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yciX4l3qMkmv7AY+8O6tPlOWGH29mDQOHc18Ms+c/wy3+db7H6aFSsYhhefgtrl4eoayR7WU0B8NrozohiTuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:36:26.966041Z","bundle_sha256":"69220ccfae7711183f9aec2196421db0459bbb6b02ef11dd9159e9a93de2a125"}}