{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:F37GPVIEL7MCJBLROEKJME2ZTB","short_pith_number":"pith:F37GPVIE","canonical_record":{"source":{"id":"1802.03133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-09T05:19:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"96d10f8ad3c2268eba7db124a90efaeb40b72dc9b649fd9923de77824e2b4bfc","abstract_canon_sha256":"7d6877ddb1d468b1d13fd20b347bb6bfa4921591cff2353dae361e195b449e87"},"schema_version":"1.0"},"canonical_sha256":"2efe67d5045fd824857171149613599864f9727ae0eb6d9f242dfcb97622005c","source":{"kind":"arxiv","id":"1802.03133","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03133","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03133v2","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03133","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"F37GPVIEL7MC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"F37GPVIEL7MCJBLR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"F37GPVIE","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:F37GPVIEL7MCJBLROEKJME2ZTB","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-09T05:19:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"96d10f8ad3c2268eba7db124a90efaeb40b72dc9b649fd9923de77824e2b4bfc","abstract_canon_sha256":"7d6877ddb1d468b1d13fd20b347bb6bfa4921591cff2353dae361e195b449e87"},"schema_version":"1.0"},"canonical_sha256":"2efe67d5045fd824857171149613599864f9727ae0eb6d9f242dfcb97622005c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:18.317798Z","signature_b64":"/e+40ncejWDZJX78Xa4GGBceBokUGoMHFL3kQWGcfxbgDoLddonIyZQUrznJUzhPcBP93QSMDCvzJKYPz9+FBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2efe67d5045fd824857171149613599864f9727ae0eb6d9f242dfcb97622005c","last_reissued_at":"2026-05-18T00:22:18.317347Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:18.317347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03133","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9rOYxFI/5q3LTCHxf15XFQUOegn6oTLRLT05xkflQgaHD9amH+PcrQ1+BMydfDnKKXY+yfeI6Lsf7jhmWnjuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:37:40.420625Z"},"content_sha256":"1657918ee85c144863f5ae176e604f401be296091a6c2c830d1f587737324b78","schema_version":"1.0","event_id":"sha256:1657918ee85c144863f5ae176e604f401be296091a6c2c830d1f587737324b78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:F37GPVIEL7MCJBLROEKJME2ZTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Guangrun Wang, Jiefeng Peng, Liang Lin, Ping Luo, Xinjiang Wang","submitted_at":"2018-02-09T05:19:16Z","abstract_excerpt":"As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with scenario of micro-batch (e.g., less than 10 samples in a mini-batch), since the estimated statistics in a mini-batch are not reliable with insufficient samples. In this paper, we present a novel normalization method, called Batch Kalman Normalization (BKN), for improving and accelerating the training of DNNs, parti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03133","kind":"arxiv","version":2},"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":"2026-05-18T00:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NPczYhI7BswpeNkhTv4T9wU/mduPSGBYxiddZO8c2IBy1KL6G9o0DzD6542m7r39MEtxlHEMzEkNKzXTnCaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:37:40.421429Z"},"content_sha256":"44a15b0e6056cc4544d72cf7cfd3af9c27db8e3dc01784a6835f99f1f8844e01","schema_version":"1.0","event_id":"sha256:44a15b0e6056cc4544d72cf7cfd3af9c27db8e3dc01784a6835f99f1f8844e01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F37GPVIEL7MCJBLROEKJME2ZTB/bundle.json","state_url":"https://pith.science/pith/F37GPVIEL7MCJBLROEKJME2ZTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F37GPVIEL7MCJBLROEKJME2ZTB/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":"2026-06-01T02:37:40Z","links":{"resolver":"https://pith.science/pith/F37GPVIEL7MCJBLROEKJME2ZTB","bundle":"https://pith.science/pith/F37GPVIEL7MCJBLROEKJME2ZTB/bundle.json","state":"https://pith.science/pith/F37GPVIEL7MCJBLROEKJME2ZTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F37GPVIEL7MCJBLROEKJME2ZTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:F37GPVIEL7MCJBLROEKJME2ZTB","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":"7d6877ddb1d468b1d13fd20b347bb6bfa4921591cff2353dae361e195b449e87","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-09T05:19:16Z","title_canon_sha256":"96d10f8ad3c2268eba7db124a90efaeb40b72dc9b649fd9923de77824e2b4bfc"},"schema_version":"1.0","source":{"id":"1802.03133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03133","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03133v2","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03133","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"F37GPVIEL7MC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"F37GPVIEL7MCJBLR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"F37GPVIE","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:44a15b0e6056cc4544d72cf7cfd3af9c27db8e3dc01784a6835f99f1f8844e01","target":"graph","created_at":"2026-05-18T00:22:18Z","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":"As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with scenario of micro-batch (e.g., less than 10 samples in a mini-batch), since the estimated statistics in a mini-batch are not reliable with insufficient samples. In this paper, we present a novel normalization method, called Batch Kalman Normalization (BKN), for improving and accelerating the training of DNNs, parti","authors_text":"Guangrun Wang, Jiefeng Peng, Liang Lin, Ping Luo, Xinjiang Wang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-09T05:19:16Z","title":"Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03133","kind":"arxiv","version":2},"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":"sha256:1657918ee85c144863f5ae176e604f401be296091a6c2c830d1f587737324b78","target":"record","created_at":"2026-05-18T00:22:18Z","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":"7d6877ddb1d468b1d13fd20b347bb6bfa4921591cff2353dae361e195b449e87","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-09T05:19:16Z","title_canon_sha256":"96d10f8ad3c2268eba7db124a90efaeb40b72dc9b649fd9923de77824e2b4bfc"},"schema_version":"1.0","source":{"id":"1802.03133","kind":"arxiv","version":2}},"canonical_sha256":"2efe67d5045fd824857171149613599864f9727ae0eb6d9f242dfcb97622005c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2efe67d5045fd824857171149613599864f9727ae0eb6d9f242dfcb97622005c","first_computed_at":"2026-05-18T00:22:18.317347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:18.317347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/e+40ncejWDZJX78Xa4GGBceBokUGoMHFL3kQWGcfxbgDoLddonIyZQUrznJUzhPcBP93QSMDCvzJKYPz9+FBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:18.317798Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1657918ee85c144863f5ae176e604f401be296091a6c2c830d1f587737324b78","sha256:44a15b0e6056cc4544d72cf7cfd3af9c27db8e3dc01784a6835f99f1f8844e01"],"state_sha256":"9e4888ba934acfbf4b229c0de52a7bdceae86cedc23a0f27eafad4f2f8518fee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o6McgxbkvADj0nhUPVwGTcEpwJw8a2wjPR3mcPxMJ2I1kOsr8hdi4IYxYZSix+wjOI/W5RoxfNmkXBl9Ml7NAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:37:40.425844Z","bundle_sha256":"6db1915787e6147fa00ea1a7215ff59572777f21d13a0503a8ea293889c1ce1b"}}