{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EEPG3L2MMMYRLLTXAXTWVTJMUY","short_pith_number":"pith:EEPG3L2M","schema_version":"1.0","canonical_sha256":"211e6daf4c633115ae7705e76acd2ca6311ded93e9ce3bdf9ee4aab27262475a","source":{"kind":"arxiv","id":"1806.02375","version":4},"attestation_state":"computed","paper":{"title":"Understanding Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bart Selman, Carla Gomes, Johan Bjorck, Kilian Q. Weinberger","submitted_at":"2018-06-01T03:57:56Z","abstract_excerpt":"Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks. Its tendency to improve accuracy and speed up training have established BN as a favorite technique in deep learning. Yet, despite its enormous success, there remains little consensus on the exact reason and mechanism behind these improvements. In this paper we take a step towards a better understanding of BN, following an empirical approach. We conduct several experiments, and show that BN primarily enables training with larger learning rates, which is the cause for faster convergen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1806.02375","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T03:57:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7158c83a7e4ace710857fe60d84328c3a5eed53b99291b1b9409256ea926b18e","abstract_canon_sha256":"51ab35cedc64afb2fbea1c1633d31c583de554eea615f300515ebf1ee5ac346e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:32.583845Z","signature_b64":"Ziej3DQg77Qe8K1Ftvyw0rijdUlpwzRe7W1wt3WgawTyQuQxw0AanSbva/rr+dzDFKqvOUrt9lhcFj3fUsHaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"211e6daf4c633115ae7705e76acd2ca6311ded93e9ce3bdf9ee4aab27262475a","last_reissued_at":"2026-05-17T23:59:32.583203Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:32.583203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bart Selman, Carla Gomes, Johan Bjorck, Kilian Q. Weinberger","submitted_at":"2018-06-01T03:57:56Z","abstract_excerpt":"Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks. Its tendency to improve accuracy and speed up training have established BN as a favorite technique in deep learning. Yet, despite its enormous success, there remains little consensus on the exact reason and mechanism behind these improvements. In this paper we take a step towards a better understanding of BN, following an empirical approach. We conduct several experiments, and show that BN primarily enables training with larger learning rates, which is the cause for faster convergen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02375","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.02375","created_at":"2026-05-17T23:59:32.583304+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02375v4","created_at":"2026-05-17T23:59:32.583304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02375","created_at":"2026-05-17T23:59:32.583304+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEPG3L2MMMYR","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEPG3L2MMMYRLLTX","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEPG3L2M","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00139","citing_title":"Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY","json":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY.json","graph_json":"https://pith.science/api/pith-number/EEPG3L2MMMYRLLTXAXTWVTJMUY/graph.json","events_json":"https://pith.science/api/pith-number/EEPG3L2MMMYRLLTXAXTWVTJMUY/events.json","paper":"https://pith.science/paper/EEPG3L2M"},"agent_actions":{"view_html":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY","download_json":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY.json","view_paper":"https://pith.science/paper/EEPG3L2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02375&json=true","fetch_graph":"https://pith.science/api/pith-number/EEPG3L2MMMYRLLTXAXTWVTJMUY/graph.json","fetch_events":"https://pith.science/api/pith-number/EEPG3L2MMMYRLLTXAXTWVTJMUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY/action/storage_attestation","attest_author":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY/action/author_attestation","sign_citation":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY/action/citation_signature","submit_replication":"https://pith.science/pith/EEPG3L2MMMYRLLTXAXTWVTJMUY/action/replication_record"}},"created_at":"2026-05-17T23:59:32.583304+00:00","updated_at":"2026-05-17T23:59:32.583304+00:00"}