{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZB7AGJD53XS2GTZT22WGLXKDGV","short_pith_number":"pith:ZB7AGJD5","canonical_record":{"source":{"id":"1905.05928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T03:29:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e0c4a28dcc353662ee64c855d5377296bcfd30a4f3bfe65eea45a4e2c7ccb9f","abstract_canon_sha256":"117048ad5cfb7d66f63d91f9c869c0b9f4197780e95fc00240ae6fdf2df51df4"},"schema_version":"1.0"},"canonical_sha256":"c87e03247ddde5a34f33d6ac65dd4335452a42d5e7927407f77973640a6bde28","source":{"kind":"arxiv","id":"1905.05928","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05928","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05928v1","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05928","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZB7AGJD53XS2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZB7AGJD53XS2GTZT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZB7AGJD5","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZB7AGJD53XS2GTZT22WGLXKDGV","target":"record","payload":{"canonical_record":{"source":{"id":"1905.05928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T03:29:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e0c4a28dcc353662ee64c855d5377296bcfd30a4f3bfe65eea45a4e2c7ccb9f","abstract_canon_sha256":"117048ad5cfb7d66f63d91f9c869c0b9f4197780e95fc00240ae6fdf2df51df4"},"schema_version":"1.0"},"canonical_sha256":"c87e03247ddde5a34f33d6ac65dd4335452a42d5e7927407f77973640a6bde28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:08.063633Z","signature_b64":"Td8qlJDuJOzwmg8zf2rmSmKNR8sN+Msp+n0Xp1ncVo+0NcXdlO3vgXJRIOeEieHcWypF3Hn0ukHUuszxSwN/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c87e03247ddde5a34f33d6ac65dd4335452a42d5e7927407f77973640a6bde28","last_reissued_at":"2026-05-17T23:46:08.062929Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:08.062929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.05928","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":"2026-05-17T23:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nw0LctsIqxRDeNN61J5c3QD3MKpAHIod1ztHk8GLJvI64B8p7sPxQ5+DT7G9evAZKVqVawvzQ239ocm6o3wfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T09:23:24.432136Z"},"content_sha256":"b339a68d715c0ea3d2f937441d00f2b34872154381fe51a13c0f4d47df053517","schema_version":"1.0","event_id":"sha256:b339a68d715c0ea3d2f937441d00f2b34872154381fe51a13c0f4d47df053517"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZB7AGJD53XS2GTZT22WGLXKDGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benben Liao, Chang-Yu Hsieh, Guangyong Chen, Pengfei Chen, Shengyu Zhang, Yujun Shi","submitted_at":"2019-05-15T03:29:06Z","abstract_excerpt":"In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed. Given the well-known fact that independent components must be whitened, we introduce a novel Independent-Component (IC) layer before each weight layer, whose inputs would be made more independent. However, determining independent components is a computationally intensive task. To overcome this challenge, we propose to implement an IC layer by combining two popular techniques, Batch "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05928","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":"2026-05-17T23:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uELXObOL4OaV+PVwqBzGmQHDlxkyKgfltnRrmX//qZahw9lNVewcous3E+7mPmbLVOrIvnMb5UrONtP+wL0WAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T09:23:24.432789Z"},"content_sha256":"2e0d657bcf78314f411d5fe03dc45c1292323b0d4e94e25140c26d0d7392f913","schema_version":"1.0","event_id":"sha256:2e0d657bcf78314f411d5fe03dc45c1292323b0d4e94e25140c26d0d7392f913"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZB7AGJD53XS2GTZT22WGLXKDGV/bundle.json","state_url":"https://pith.science/pith/ZB7AGJD53XS2GTZT22WGLXKDGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZB7AGJD53XS2GTZT22WGLXKDGV/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":"2026-05-19T09:23:24Z","links":{"resolver":"https://pith.science/pith/ZB7AGJD53XS2GTZT22WGLXKDGV","bundle":"https://pith.science/pith/ZB7AGJD53XS2GTZT22WGLXKDGV/bundle.json","state":"https://pith.science/pith/ZB7AGJD53XS2GTZT22WGLXKDGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZB7AGJD53XS2GTZT22WGLXKDGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZB7AGJD53XS2GTZT22WGLXKDGV","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":"117048ad5cfb7d66f63d91f9c869c0b9f4197780e95fc00240ae6fdf2df51df4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T03:29:06Z","title_canon_sha256":"6e0c4a28dcc353662ee64c855d5377296bcfd30a4f3bfe65eea45a4e2c7ccb9f"},"schema_version":"1.0","source":{"id":"1905.05928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05928","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05928v1","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05928","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZB7AGJD53XS2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZB7AGJD53XS2GTZT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZB7AGJD5","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:2e0d657bcf78314f411d5fe03dc45c1292323b0d4e94e25140c26d0d7392f913","target":"graph","created_at":"2026-05-17T23:46:08Z","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":"In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed. Given the well-known fact that independent components must be whitened, we introduce a novel Independent-Component (IC) layer before each weight layer, whose inputs would be made more independent. However, determining independent components is a computationally intensive task. To overcome this challenge, we propose to implement an IC layer by combining two popular techniques, Batch ","authors_text":"Benben Liao, Chang-Yu Hsieh, Guangyong Chen, Pengfei Chen, Shengyu Zhang, Yujun Shi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T03:29:06Z","title":"Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05928","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:b339a68d715c0ea3d2f937441d00f2b34872154381fe51a13c0f4d47df053517","target":"record","created_at":"2026-05-17T23:46:08Z","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":"117048ad5cfb7d66f63d91f9c869c0b9f4197780e95fc00240ae6fdf2df51df4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T03:29:06Z","title_canon_sha256":"6e0c4a28dcc353662ee64c855d5377296bcfd30a4f3bfe65eea45a4e2c7ccb9f"},"schema_version":"1.0","source":{"id":"1905.05928","kind":"arxiv","version":1}},"canonical_sha256":"c87e03247ddde5a34f33d6ac65dd4335452a42d5e7927407f77973640a6bde28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c87e03247ddde5a34f33d6ac65dd4335452a42d5e7927407f77973640a6bde28","first_computed_at":"2026-05-17T23:46:08.062929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:08.062929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Td8qlJDuJOzwmg8zf2rmSmKNR8sN+Msp+n0Xp1ncVo+0NcXdlO3vgXJRIOeEieHcWypF3Hn0ukHUuszxSwN/AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:08.063633Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b339a68d715c0ea3d2f937441d00f2b34872154381fe51a13c0f4d47df053517","sha256:2e0d657bcf78314f411d5fe03dc45c1292323b0d4e94e25140c26d0d7392f913"],"state_sha256":"ba84c734d2bdbc9a3841c03cb47288abc964fa6f912bfedc524b13060b9682a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOsX9K6qT+PK0OElVKb0wHzwiBPV8ujJDns4/UYODradq6cNfXoiDEkTp5mPbDVJcF4sEjGjMWZt79m/qmSxCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T09:23:24.435750Z","bundle_sha256":"b9c9b8a7bb32ec8e8d9db75e62d34a0373e2a79d19bc0abde845234fbb3290a8"}}