{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ZIRW7BPO5GIR22KP2AAIM37L4D","short_pith_number":"pith:ZIRW7BPO","canonical_record":{"source":{"id":"1512.00242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-01T12:46:11Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"7ead633384ee2c25849bce041e585b4ad87278112b7a786ef2dc516d2c317591","abstract_canon_sha256":"fe50a730ddb44e20d3d04eb027b63dc347ab4e7d426fd37ad0a63dfe16485fee"},"schema_version":"1.0"},"canonical_sha256":"ca236f85eee9911d694fd000866febe0fa22686a7894fc31b405be57004196ff","source":{"kind":"arxiv","id":"1512.00242","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.00242","created_at":"2026-05-18T01:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"1512.00242v1","created_at":"2026-05-18T01:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.00242","created_at":"2026-05-18T01:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZIRW7BPO5GIR","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZIRW7BPO5GIR22KP","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZIRW7BPO","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ZIRW7BPO5GIR22KP2AAIM37L4D","target":"record","payload":{"canonical_record":{"source":{"id":"1512.00242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-01T12:46:11Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"7ead633384ee2c25849bce041e585b4ad87278112b7a786ef2dc516d2c317591","abstract_canon_sha256":"fe50a730ddb44e20d3d04eb027b63dc347ab4e7d426fd37ad0a63dfe16485fee"},"schema_version":"1.0"},"canonical_sha256":"ca236f85eee9911d694fd000866febe0fa22686a7894fc31b405be57004196ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:32.376426Z","signature_b64":"ZNUEEe3I8lfa/yUtj5a6Yo+hP9PE4+3wwhpmsI4ao7UX0Gx/KaWurzWpxTQLyu3X1kt2NaDDDjJYRBMtE/fqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca236f85eee9911d694fd000866febe0fa22686a7894fc31b405be57004196ff","last_reissued_at":"2026-05-18T01:25:32.375497Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:32.375497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.00242","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":"2026-05-18T01:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vT7GY+VnzW/JmG3IHatq/w9dp6eXZwyIz0opW59x2RwKe5sgUaWI6YXvrjayBJ0TzBCOAkxnZEHeuXE3kXNMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:09:16.790581Z"},"content_sha256":"f112b6f4bdab19b0281038b32dff65a5362f794b8530b50e7418e98a16763b17","schema_version":"1.0","event_id":"sha256:f112b6f4bdab19b0281038b32dff65a5362f794b8530b50e7418e98a16763b17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ZIRW7BPO5GIR22KP2AAIM37L4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Dropout Training for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Haibing Wu, Xiaodong Gu","submitted_at":"2015-12-01T12:46:11Z","abstract_excerpt":"Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.00242","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":"2026-05-18T01:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6FkzYN9Z/AZx57CqishYPoMeCiu3ZkwB7JxeWiB7c2XeXhTQBrfn2Jop8phcoCB4XpOyfN5qG4r7p7JrFjIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:09:16.791224Z"},"content_sha256":"e36d08f3d6867f719987d0ef258f15fb529204d0123cb8900ea4904e83c05c7e","schema_version":"1.0","event_id":"sha256:e36d08f3d6867f719987d0ef258f15fb529204d0123cb8900ea4904e83c05c7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIRW7BPO5GIR22KP2AAIM37L4D/bundle.json","state_url":"https://pith.science/pith/ZIRW7BPO5GIR22KP2AAIM37L4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIRW7BPO5GIR22KP2AAIM37L4D/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":"2026-05-31T06:09:16Z","links":{"resolver":"https://pith.science/pith/ZIRW7BPO5GIR22KP2AAIM37L4D","bundle":"https://pith.science/pith/ZIRW7BPO5GIR22KP2AAIM37L4D/bundle.json","state":"https://pith.science/pith/ZIRW7BPO5GIR22KP2AAIM37L4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIRW7BPO5GIR22KP2AAIM37L4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ZIRW7BPO5GIR22KP2AAIM37L4D","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":"fe50a730ddb44e20d3d04eb027b63dc347ab4e7d426fd37ad0a63dfe16485fee","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-01T12:46:11Z","title_canon_sha256":"7ead633384ee2c25849bce041e585b4ad87278112b7a786ef2dc516d2c317591"},"schema_version":"1.0","source":{"id":"1512.00242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.00242","created_at":"2026-05-18T01:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"1512.00242v1","created_at":"2026-05-18T01:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.00242","created_at":"2026-05-18T01:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZIRW7BPO5GIR","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZIRW7BPO5GIR22KP","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZIRW7BPO","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:e36d08f3d6867f719987d0ef258f15fb529204d0123cb8900ea4904e83c05c7e","target":"graph","created_at":"2026-05-18T01:25:32Z","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, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of ","authors_text":"Haibing Wu, Xiaodong Gu","cross_cats":["cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-01T12:46:11Z","title":"Towards Dropout Training for Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.00242","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:f112b6f4bdab19b0281038b32dff65a5362f794b8530b50e7418e98a16763b17","target":"record","created_at":"2026-05-18T01:25:32Z","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":"fe50a730ddb44e20d3d04eb027b63dc347ab4e7d426fd37ad0a63dfe16485fee","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-01T12:46:11Z","title_canon_sha256":"7ead633384ee2c25849bce041e585b4ad87278112b7a786ef2dc516d2c317591"},"schema_version":"1.0","source":{"id":"1512.00242","kind":"arxiv","version":1}},"canonical_sha256":"ca236f85eee9911d694fd000866febe0fa22686a7894fc31b405be57004196ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca236f85eee9911d694fd000866febe0fa22686a7894fc31b405be57004196ff","first_computed_at":"2026-05-18T01:25:32.375497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:32.375497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZNUEEe3I8lfa/yUtj5a6Yo+hP9PE4+3wwhpmsI4ao7UX0Gx/KaWurzWpxTQLyu3X1kt2NaDDDjJYRBMtE/fqBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:32.376426Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.00242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f112b6f4bdab19b0281038b32dff65a5362f794b8530b50e7418e98a16763b17","sha256:e36d08f3d6867f719987d0ef258f15fb529204d0123cb8900ea4904e83c05c7e"],"state_sha256":"f622827a6cb699966016ec4af9ac8cae45f4f8b4cd48d62a8fa1a28e0dec1c23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oX3hzWSQhkl0jg6kjAv+QWEO/euE3+WTLDr5YRvrh+krRBo/fBT5Y/LIVbT3AgqHtH+sEs0athTg0Sr/9pwcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:09:16.794593Z","bundle_sha256":"b9c76ed928cccc7bd9c6c091ffcc2f1bbf31ea7ddb7c79c15d62b4363aa9bcd7"}}