{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CGEUV2UK5SVNXX22XRXGJ6NSYV","short_pith_number":"pith:CGEUV2UK","canonical_record":{"source":{"id":"1810.00091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T21:42:38Z","cross_cats_sorted":[],"title_canon_sha256":"0e9b7bdeb32280584314d4fd6e74fe30d5854ec6030422fcb0ddeb5bd22cb2c3","abstract_canon_sha256":"34ba411b6369d64d898a0377c14224075922c6bc434a4043188e09b72b33383d"},"schema_version":"1.0"},"canonical_sha256":"11894aea8aecaadbdf5abc6e64f9b2c56ce09148b615fbb376f453731c34c2b7","source":{"kind":"arxiv","id":"1810.00091","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00091","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00091v1","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00091","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"CGEUV2UK5SVN","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CGEUV2UK5SVNXX22","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CGEUV2UK","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CGEUV2UK5SVNXX22XRXGJ6NSYV","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T21:42:38Z","cross_cats_sorted":[],"title_canon_sha256":"0e9b7bdeb32280584314d4fd6e74fe30d5854ec6030422fcb0ddeb5bd22cb2c3","abstract_canon_sha256":"34ba411b6369d64d898a0377c14224075922c6bc434a4043188e09b72b33383d"},"schema_version":"1.0"},"canonical_sha256":"11894aea8aecaadbdf5abc6e64f9b2c56ce09148b615fbb376f453731c34c2b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:28.827374Z","signature_b64":"OGfc5BDbgVjdeORyCSfDikYmALXuqgTG3vaZShTvatEr+tCIkTIrqPkgww96XfhH/7X9ISgS1rskyLGie3LbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11894aea8aecaadbdf5abc6e64f9b2c56ce09148b615fbb376f453731c34c2b7","last_reissued_at":"2026-05-18T00:04:28.826810Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:28.826810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00091","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":"2026-05-18T00:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0factDPPIiJaoExp1ptmt4D2t4IgYBAL5pnV2aA85OnqgH0r0HHk8IY3SCipjQ3KbMBb6lRS6cMboWOeqELDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:25:07.628461Z"},"content_sha256":"7cb700a8f6cfe4342c1573c428cae0c250aaed8c733080934678266bde76ead7","schema_version":"1.0","event_id":"sha256:7cb700a8f6cfe4342c1573c428cae0c250aaed8c733080934678266bde76ead7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CGEUV2UK5SVNXX22XRXGJ6NSYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyuan Feng, Kun Wan, Lingwei Xie, Yufei Ding","submitted_at":"2018-09-28T21:42:38Z","abstract_excerpt":"Recently convolutional neural networks (CNNs) achieve great accuracy in visual recognition tasks. DenseNet becomes one of the most popular CNN models due to its effectiveness in feature-reuse. However, like other CNN models, DenseNets also face overfitting problem if not severer. Existing dropout method can be applied but not as effective due to the introduced nonlinear connections. In particular, the property of feature-reuse in DenseNet will be impeded, and the dropout effect will be weakened by the spatial correlation inside feature maps. To address these problems, we craft the design of a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00091","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":"2026-05-18T00:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+k/KlNBBBv4PHEfd95wr7itlV2Hov7Mj2FKv0xh0uS+k8u9y990WZb1peCYuHa5YAhyK4r36LbVs7EcWloLPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:25:07.629068Z"},"content_sha256":"e8fabc3b581f58e76222e8abd13dbbb537ac15d9e36c6ce27917a642b71a9b7a","schema_version":"1.0","event_id":"sha256:e8fabc3b581f58e76222e8abd13dbbb537ac15d9e36c6ce27917a642b71a9b7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV/bundle.json","state_url":"https://pith.science/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV/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":"2026-06-04T04:25:07Z","links":{"resolver":"https://pith.science/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV","bundle":"https://pith.science/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV/bundle.json","state":"https://pith.science/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGEUV2UK5SVNXX22XRXGJ6NSYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CGEUV2UK5SVNXX22XRXGJ6NSYV","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":"34ba411b6369d64d898a0377c14224075922c6bc434a4043188e09b72b33383d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T21:42:38Z","title_canon_sha256":"0e9b7bdeb32280584314d4fd6e74fe30d5854ec6030422fcb0ddeb5bd22cb2c3"},"schema_version":"1.0","source":{"id":"1810.00091","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00091","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00091v1","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00091","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"CGEUV2UK5SVN","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CGEUV2UK5SVNXX22","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CGEUV2UK","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:e8fabc3b581f58e76222e8abd13dbbb537ac15d9e36c6ce27917a642b71a9b7a","target":"graph","created_at":"2026-05-18T00:04:28Z","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":"Recently convolutional neural networks (CNNs) achieve great accuracy in visual recognition tasks. DenseNet becomes one of the most popular CNN models due to its effectiveness in feature-reuse. However, like other CNN models, DenseNets also face overfitting problem if not severer. Existing dropout method can be applied but not as effective due to the introduced nonlinear connections. In particular, the property of feature-reuse in DenseNet will be impeded, and the dropout effect will be weakened by the spatial correlation inside feature maps. To address these problems, we craft the design of a ","authors_text":"Boyuan Feng, Kun Wan, Lingwei Xie, Yufei Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T21:42:38Z","title":"Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00091","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":"sha256:7cb700a8f6cfe4342c1573c428cae0c250aaed8c733080934678266bde76ead7","target":"record","created_at":"2026-05-18T00:04:28Z","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":"34ba411b6369d64d898a0377c14224075922c6bc434a4043188e09b72b33383d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T21:42:38Z","title_canon_sha256":"0e9b7bdeb32280584314d4fd6e74fe30d5854ec6030422fcb0ddeb5bd22cb2c3"},"schema_version":"1.0","source":{"id":"1810.00091","kind":"arxiv","version":1}},"canonical_sha256":"11894aea8aecaadbdf5abc6e64f9b2c56ce09148b615fbb376f453731c34c2b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11894aea8aecaadbdf5abc6e64f9b2c56ce09148b615fbb376f453731c34c2b7","first_computed_at":"2026-05-18T00:04:28.826810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:28.826810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OGfc5BDbgVjdeORyCSfDikYmALXuqgTG3vaZShTvatEr+tCIkTIrqPkgww96XfhH/7X9ISgS1rskyLGie3LbDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:28.827374Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00091","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb700a8f6cfe4342c1573c428cae0c250aaed8c733080934678266bde76ead7","sha256:e8fabc3b581f58e76222e8abd13dbbb537ac15d9e36c6ce27917a642b71a9b7a"],"state_sha256":"dcb039d6b1ac5904ee9e25a0c73ba7dbcc309ce337b37092213fd2c18fb0bab1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgswlINsThW/0TazPahHInxdhs5pETr3BZRXYMxXI7UzqgYBWS0zFl2sVxp6/7pXhDo/1ROxad62wk1Uq5LoDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T04:25:07.632489Z","bundle_sha256":"dc56dd290626eb944d09993d7d999585e1d879428a4a3730d15962b0ff3269fe"}}