{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:KA4VTLVZVZBBKZJ2HNEPU5FLVK","short_pith_number":"pith:KA4VTLVZ","canonical_record":{"source":{"id":"1507.08754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-31T05:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"0e54574efff5e48db5916493e05989ff6c97472bbf79c281fb265dac326877e8","abstract_canon_sha256":"707fb9820975df97dc44326b76b97b61f6d3f771e7f9d6d87f292eb66d539a06"},"schema_version":"1.0"},"canonical_sha256":"503959aeb9ae4215653a3b48fa74abaab291a7ca38cd85ec833baf811f48da63","source":{"kind":"arxiv","id":"1507.08754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08754","created_at":"2026-05-18T01:36:02Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08754v1","created_at":"2026-05-18T01:36:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08754","created_at":"2026-05-18T01:36:02Z"},{"alias_kind":"pith_short_12","alias_value":"KA4VTLVZVZBB","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KA4VTLVZVZBBKZJ2","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KA4VTLVZ","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:KA4VTLVZVZBBKZJ2HNEPU5FLVK","target":"record","payload":{"canonical_record":{"source":{"id":"1507.08754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-31T05:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"0e54574efff5e48db5916493e05989ff6c97472bbf79c281fb265dac326877e8","abstract_canon_sha256":"707fb9820975df97dc44326b76b97b61f6d3f771e7f9d6d87f292eb66d539a06"},"schema_version":"1.0"},"canonical_sha256":"503959aeb9ae4215653a3b48fa74abaab291a7ca38cd85ec833baf811f48da63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:02.934432Z","signature_b64":"83HVsCK33LfH8ZyiKZtbChYkJSz28ft42umQ3XWfDNkndQknx+zbcqJJi9Zr35Xbl83sVoGc4sWxBDBkoyliAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"503959aeb9ae4215653a3b48fa74abaab291a7ca38cd85ec833baf811f48da63","last_reissued_at":"2026-05-18T01:36:02.933849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:02.933849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.08754","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":"2026-05-18T01:36:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUOM+B5yTinY+q5omS5Nxs4a7N4h0FtLBXHBCAZBZOZ+gFslMuP0BXCoyC6EAgwVav1M0ARw4aM2OI96QCBwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T18:41:29.629578Z"},"content_sha256":"9e058387efaf31012415c33913977d36714de9b3a0895b5d9101fd5d9a67f953","schema_version":"1.0","event_id":"sha256:9e058387efaf31012415c33913977d36714de9b3a0895b5d9101fd5d9a67f953"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:KA4VTLVZVZBBKZJ2HNEPU5FLVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dexing Kong, Fa Wu, Peijun Hu","submitted_at":"2015-07-31T05:02:56Z","abstract_excerpt":"This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep neural networks from overfitting by randomly dropping units during training. Our sDropout randomly splits the data into two subsets and keeps both rather than discards one subset. We also introduce two rotational convolution techniques, i.e. rotate-pooling convolution (RPC) and flip-rotate-pooling convolution (FRPC) to boost CNNs' performance on the robustness fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08754","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":"2026-05-18T01:36:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NoTnaxa7nQ7ko1knBbUydpA2Jd0rM5wyvylNhnL8C1GbZYde0VW0OY1FBGMkjduzkvFyzfg30Zep9ufqD7ZiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T18:41:29.629916Z"},"content_sha256":"9d20c2efb1f3e40182b830a2858a15dd7b1ab3ecd165094a4a7f424fa17154e9","schema_version":"1.0","event_id":"sha256:9d20c2efb1f3e40182b830a2858a15dd7b1ab3ecd165094a4a7f424fa17154e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK/bundle.json","state_url":"https://pith.science/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK/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":"2026-06-27T18:41:29Z","links":{"resolver":"https://pith.science/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK","bundle":"https://pith.science/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK/bundle.json","state":"https://pith.science/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KA4VTLVZVZBBKZJ2HNEPU5FLVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:KA4VTLVZVZBBKZJ2HNEPU5FLVK","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":"707fb9820975df97dc44326b76b97b61f6d3f771e7f9d6d87f292eb66d539a06","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-31T05:02:56Z","title_canon_sha256":"0e54574efff5e48db5916493e05989ff6c97472bbf79c281fb265dac326877e8"},"schema_version":"1.0","source":{"id":"1507.08754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08754","created_at":"2026-05-18T01:36:02Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08754v1","created_at":"2026-05-18T01:36:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08754","created_at":"2026-05-18T01:36:02Z"},{"alias_kind":"pith_short_12","alias_value":"KA4VTLVZVZBB","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KA4VTLVZVZBBKZJ2","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KA4VTLVZ","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:9d20c2efb1f3e40182b830a2858a15dd7b1ab3ecd165094a4a7f424fa17154e9","target":"graph","created_at":"2026-05-18T01:36:02Z","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":"This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep neural networks from overfitting by randomly dropping units during training. Our sDropout randomly splits the data into two subsets and keeps both rather than discards one subset. We also introduce two rotational convolution techniques, i.e. rotate-pooling convolution (RPC) and flip-rotate-pooling convolution (FRPC) to boost CNNs' performance on the robustness fo","authors_text":"Dexing Kong, Fa Wu, Peijun Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-31T05:02:56Z","title":"Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08754","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":"sha256:9e058387efaf31012415c33913977d36714de9b3a0895b5d9101fd5d9a67f953","target":"record","created_at":"2026-05-18T01:36:02Z","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":"707fb9820975df97dc44326b76b97b61f6d3f771e7f9d6d87f292eb66d539a06","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-31T05:02:56Z","title_canon_sha256":"0e54574efff5e48db5916493e05989ff6c97472bbf79c281fb265dac326877e8"},"schema_version":"1.0","source":{"id":"1507.08754","kind":"arxiv","version":1}},"canonical_sha256":"503959aeb9ae4215653a3b48fa74abaab291a7ca38cd85ec833baf811f48da63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"503959aeb9ae4215653a3b48fa74abaab291a7ca38cd85ec833baf811f48da63","first_computed_at":"2026-05-18T01:36:02.933849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:02.933849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"83HVsCK33LfH8ZyiKZtbChYkJSz28ft42umQ3XWfDNkndQknx+zbcqJJi9Zr35Xbl83sVoGc4sWxBDBkoyliAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:02.934432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.08754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e058387efaf31012415c33913977d36714de9b3a0895b5d9101fd5d9a67f953","sha256:9d20c2efb1f3e40182b830a2858a15dd7b1ab3ecd165094a4a7f424fa17154e9"],"state_sha256":"baf4f7ab3718b17c1d5ee5ebfd3326ca747bcf63cfa0b059546fc62316bd63b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iVc0RoRPc5JtahexiL/bgKcZJhlCmomL2AptxrcE9KcswyJrQSX55JO3dp+6g7CRLXmAe9XOD5Cw9PpT91+SAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T18:41:29.632181Z","bundle_sha256":"3ca77a4093358408849a590f570ee48504b544cde32ba43a3e2db52664176b4f"}}