{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LTMDGWYJA4MSGOHWMZF2WQKLGS","short_pith_number":"pith:LTMDGWYJ","schema_version":"1.0","canonical_sha256":"5cd8335b0907192338f6664bab414b34bd8f8a0d910f27a9f6e253072b2591f0","source":{"kind":"arxiv","id":"2412.02843","version":1},"attestation_state":"computed","paper":{"title":"Batch Normalization Decomposed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Anatoly Khina, Ido Nachum, Marco Bondaschi, Michael Gastpar","submitted_at":"2024-12-03T21:18:27Z","abstract_excerpt":"\\emph{Batch normalization} is a successful building block of neural network architectures. Yet, it is not well understood. A neural network layer with batch normalization comprises three components that affect the representation induced by the network: \\emph{recentering} the mean of the representation to zero, \\emph{rescaling} the variance of the representation to one, and finally applying a \\emph{non-linearity}. Our work follows the work of Hadi Daneshmand, Amir Joudaki, Francis Bach [NeurIPS~'21], which studied deep \\emph{linear} neural networks with only the rescaling stage between layers a"},"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":"2412.02843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T21:18:27Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"b1bf896f07a17353f4e1e6afccfd504220a1b973048400a599df9c40384e9ec6","abstract_canon_sha256":"80b4111f1e98053f0c61fcf662f7b48e72f586ac288d43b9b95a919f5178d118"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:20.500684Z","signature_b64":"nHA9KVS0/G6kmB2qAWU+cV264Wt1YVZ1ox3bWnd7shCH7Q6JqzgUJuJVbLSPoowYAcyXT7L/ejro1z4Yq1GoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cd8335b0907192338f6664bab414b34bd8f8a0d910f27a9f6e253072b2591f0","last_reissued_at":"2026-07-05T09:44:20.500251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:20.500251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Batch Normalization Decomposed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Anatoly Khina, Ido Nachum, Marco Bondaschi, Michael Gastpar","submitted_at":"2024-12-03T21:18:27Z","abstract_excerpt":"\\emph{Batch normalization} is a successful building block of neural network architectures. Yet, it is not well understood. A neural network layer with batch normalization comprises three components that affect the representation induced by the network: \\emph{recentering} the mean of the representation to zero, \\emph{rescaling} the variance of the representation to one, and finally applying a \\emph{non-linearity}. Our work follows the work of Hadi Daneshmand, Amir Joudaki, Francis Bach [NeurIPS~'21], which studied deep \\emph{linear} neural networks with only the rescaling stage between layers a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02843","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.02843/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2412.02843","created_at":"2026-07-05T09:44:20.500323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02843v1","created_at":"2026-07-05T09:44:20.500323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02843","created_at":"2026-07-05T09:44:20.500323+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTMDGWYJA4MS","created_at":"2026-07-05T09:44:20.500323+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTMDGWYJA4MSGOHW","created_at":"2026-07-05T09:44:20.500323+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTMDGWYJ","created_at":"2026-07-05T09:44:20.500323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS","json":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS.json","graph_json":"https://pith.science/api/pith-number/LTMDGWYJA4MSGOHWMZF2WQKLGS/graph.json","events_json":"https://pith.science/api/pith-number/LTMDGWYJA4MSGOHWMZF2WQKLGS/events.json","paper":"https://pith.science/paper/LTMDGWYJ"},"agent_actions":{"view_html":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS","download_json":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS.json","view_paper":"https://pith.science/paper/LTMDGWYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02843&json=true","fetch_graph":"https://pith.science/api/pith-number/LTMDGWYJA4MSGOHWMZF2WQKLGS/graph.json","fetch_events":"https://pith.science/api/pith-number/LTMDGWYJA4MSGOHWMZF2WQKLGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS/action/storage_attestation","attest_author":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS/action/author_attestation","sign_citation":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS/action/citation_signature","submit_replication":"https://pith.science/pith/LTMDGWYJA4MSGOHWMZF2WQKLGS/action/replication_record"}},"created_at":"2026-07-05T09:44:20.500323+00:00","updated_at":"2026-07-05T09:44:20.500323+00:00"}