{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R6GHZT2I56TE5TIHB5YLYBDUX3","short_pith_number":"pith:R6GHZT2I","canonical_record":{"source":{"id":"1906.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-26T12:50:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5680d271e8726c5b0527c401c213694e0599dd7724be82168d19a0ff1648acf7","abstract_canon_sha256":"d7dda62df757fa318a717abb4d3868a7edb0f7e7391fe9cbd26b9f834f66c3be"},"schema_version":"1.0"},"canonical_sha256":"8f8c7ccf48efa64ecd070f70bc0474bece77f4dda10a998b7a44f38e62cd4158","source":{"kind":"arxiv","id":"1906.11052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11052","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11052v1","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11052","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"R6GHZT2I56TE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R6GHZT2I56TE5TIH","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R6GHZT2I","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R6GHZT2I56TE5TIHB5YLYBDUX3","target":"record","payload":{"canonical_record":{"source":{"id":"1906.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-26T12:50:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5680d271e8726c5b0527c401c213694e0599dd7724be82168d19a0ff1648acf7","abstract_canon_sha256":"d7dda62df757fa318a717abb4d3868a7edb0f7e7391fe9cbd26b9f834f66c3be"},"schema_version":"1.0"},"canonical_sha256":"8f8c7ccf48efa64ecd070f70bc0474bece77f4dda10a998b7a44f38e62cd4158","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:10.071360Z","signature_b64":"ChSk9a8O+QoX8Ajd4JvR/PnAZti7mlDJCmymXqPtkjKJbXWX0GMPCFIuoXR2FZXxl/gX/QPbO3NE9/0gpMIGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8c7ccf48efa64ecd070f70bc0474bece77f4dda10a998b7a44f38e62cd4158","last_reissued_at":"2026-05-17T23:42:10.070649Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:10.070649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.11052","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":"2026-05-17T23:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BkMO4KN4aiOUuOmWIbrXR9TwCzxzMtRkyeFI8u1GhPE/pAMpR516KH2RZOKSOx+FDcuJEY9FInX1Xy/9lRA+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T04:29:37.138845Z"},"content_sha256":"212231664672a144617501f160808fd87afa970510dd7aa2ef53582e6fbdfbb9","schema_version":"1.0","event_id":"sha256:212231664672a144617501f160808fd87afa970510dd7aa2ef53582e6fbdfbb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R6GHZT2I56TE5TIHB5YLYBDUX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Further advantages of data augmentation on convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Hern\\'andez-Garc\\'ia, Peter K\\\"onig","submitted_at":"2019-06-26T12:50:13Z","abstract_excerpt":"Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11052","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":"2026-05-17T23:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+fIWgg9oqEKQYonJ6Wy4mDpF67S48a+9DwxieHpDBP9MHSRwE3FSEz2si5JkX6+78llzpfpY5iW+D/E8msIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T04:29:37.139202Z"},"content_sha256":"6ccc330001d6fe62aa17cacd824722a39fc8e25ea4ec902644954205188963e4","schema_version":"1.0","event_id":"sha256:6ccc330001d6fe62aa17cacd824722a39fc8e25ea4ec902644954205188963e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6GHZT2I56TE5TIHB5YLYBDUX3/bundle.json","state_url":"https://pith.science/pith/R6GHZT2I56TE5TIHB5YLYBDUX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6GHZT2I56TE5TIHB5YLYBDUX3/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":"2026-05-31T04:29:37Z","links":{"resolver":"https://pith.science/pith/R6GHZT2I56TE5TIHB5YLYBDUX3","bundle":"https://pith.science/pith/R6GHZT2I56TE5TIHB5YLYBDUX3/bundle.json","state":"https://pith.science/pith/R6GHZT2I56TE5TIHB5YLYBDUX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6GHZT2I56TE5TIHB5YLYBDUX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R6GHZT2I56TE5TIHB5YLYBDUX3","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":"d7dda62df757fa318a717abb4d3868a7edb0f7e7391fe9cbd26b9f834f66c3be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-26T12:50:13Z","title_canon_sha256":"5680d271e8726c5b0527c401c213694e0599dd7724be82168d19a0ff1648acf7"},"schema_version":"1.0","source":{"id":"1906.11052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11052","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11052v1","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11052","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"R6GHZT2I56TE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R6GHZT2I56TE5TIH","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R6GHZT2I","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:6ccc330001d6fe62aa17cacd824722a39fc8e25ea4ec902644954205188963e4","target":"graph","created_at":"2026-05-17T23:42:10Z","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":"Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we ","authors_text":"Alex Hern\\'andez-Garc\\'ia, Peter K\\\"onig","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-26T12:50:13Z","title":"Further advantages of data augmentation on convolutional neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11052","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":"sha256:212231664672a144617501f160808fd87afa970510dd7aa2ef53582e6fbdfbb9","target":"record","created_at":"2026-05-17T23:42:10Z","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":"d7dda62df757fa318a717abb4d3868a7edb0f7e7391fe9cbd26b9f834f66c3be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-26T12:50:13Z","title_canon_sha256":"5680d271e8726c5b0527c401c213694e0599dd7724be82168d19a0ff1648acf7"},"schema_version":"1.0","source":{"id":"1906.11052","kind":"arxiv","version":1}},"canonical_sha256":"8f8c7ccf48efa64ecd070f70bc0474bece77f4dda10a998b7a44f38e62cd4158","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8c7ccf48efa64ecd070f70bc0474bece77f4dda10a998b7a44f38e62cd4158","first_computed_at":"2026-05-17T23:42:10.070649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:10.070649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ChSk9a8O+QoX8Ajd4JvR/PnAZti7mlDJCmymXqPtkjKJbXWX0GMPCFIuoXR2FZXxl/gX/QPbO3NE9/0gpMIGBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:10.071360Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.11052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:212231664672a144617501f160808fd87afa970510dd7aa2ef53582e6fbdfbb9","sha256:6ccc330001d6fe62aa17cacd824722a39fc8e25ea4ec902644954205188963e4"],"state_sha256":"e2978548f74b1d370b6386c1edbf6b8a81cd7209d004b2438df83cb03d2cccb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WALLFOZcQVdYrdee3tLa0SgxDLaD3fV4zW4s+kHB6YOVXR2D3xHla9jNveBH0my5da7HPsijuxoeaqiaFdfiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T04:29:37.141207Z","bundle_sha256":"ffd8b9a67fd9f7cb6604db83b209ac4b360c5f551559884a498bbb0ef1b0a0c0"}}