{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:53NQJAKFPKLMDW6DGPDMMYWNOO","short_pith_number":"pith:53NQJAKF","schema_version":"1.0","canonical_sha256":"eedb0481457a96c1dbc333c6c662cd7388dcaf0d02b9dfc0df047dba98dca49d","source":{"kind":"arxiv","id":"2009.12836","version":1},"attestation_state":"computed","paper":{"title":"Normalization Techniques in Training DNNs: Methodology, Analysis and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Zhu, Jie Qin, Lei Huang, Li Liu, Ling Shao, Yi Zhou","submitted_at":"2020-09-27T13:06:52Z","abstract_excerpt":"Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications. This paper reviews and comments on the past, present and future of normalization methods in the context of DNN training. We provide a unified picture of the main motivation behind different approaches from the perspective of optimization, and present a taxonomy for understanding the similarities and differences between them. Specifically, we decompose the pipeline of the most representative normalizing act"},"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":"2009.12836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-27T13:06:52Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2f5db98ff6b6a62ad4950952286a88ca9f193c1613359d71195c4075f73070aa","abstract_canon_sha256":"2f83bc1002b9cc07f5cb8833adb7de2839957c669f9cfba7ad00f2fb78ba34ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:24.015353Z","signature_b64":"5pCsTWNV9vLC5NPUgE+dEK8B2wJ8pswlnSFfCdYvGJZ6vsq1qs69Kbb7oTQ4HDh2etdaJOMi0H0t6b9L63e/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eedb0481457a96c1dbc333c6c662cd7388dcaf0d02b9dfc0df047dba98dca49d","last_reissued_at":"2026-07-05T01:38:24.014890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:24.014890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalization Techniques in Training DNNs: Methodology, Analysis and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Zhu, Jie Qin, Lei Huang, Li Liu, Ling Shao, Yi Zhou","submitted_at":"2020-09-27T13:06:52Z","abstract_excerpt":"Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications. This paper reviews and comments on the past, present and future of normalization methods in the context of DNN training. We provide a unified picture of the main motivation behind different approaches from the perspective of optimization, and present a taxonomy for understanding the similarities and differences between them. Specifically, we decompose the pipeline of the most representative normalizing act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12836","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/2009.12836/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":"2009.12836","created_at":"2026-07-05T01:38:24.014960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.12836v1","created_at":"2026-07-05T01:38:24.014960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12836","created_at":"2026-07-05T01:38:24.014960+00:00"},{"alias_kind":"pith_short_12","alias_value":"53NQJAKFPKLM","created_at":"2026-07-05T01:38:24.014960+00:00"},{"alias_kind":"pith_short_16","alias_value":"53NQJAKFPKLMDW6D","created_at":"2026-07-05T01:38:24.014960+00:00"},{"alias_kind":"pith_short_8","alias_value":"53NQJAKF","created_at":"2026-07-05T01:38:24.014960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25625","citing_title":"MoTIF: A Mode-Structured Tensor Framework for Multi-Parametric Approximation, Super-Resolution and Forecasting of Unsteady Systems","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09733","citing_title":"Error-mitigated quantum state tomography using neural networks","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2206.00364","citing_title":"Elucidating the Design Space of Diffusion-Based Generative Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO","json":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO.json","graph_json":"https://pith.science/api/pith-number/53NQJAKFPKLMDW6DGPDMMYWNOO/graph.json","events_json":"https://pith.science/api/pith-number/53NQJAKFPKLMDW6DGPDMMYWNOO/events.json","paper":"https://pith.science/paper/53NQJAKF"},"agent_actions":{"view_html":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO","download_json":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO.json","view_paper":"https://pith.science/paper/53NQJAKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.12836&json=true","fetch_graph":"https://pith.science/api/pith-number/53NQJAKFPKLMDW6DGPDMMYWNOO/graph.json","fetch_events":"https://pith.science/api/pith-number/53NQJAKFPKLMDW6DGPDMMYWNOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO/action/storage_attestation","attest_author":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO/action/author_attestation","sign_citation":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO/action/citation_signature","submit_replication":"https://pith.science/pith/53NQJAKFPKLMDW6DGPDMMYWNOO/action/replication_record"}},"created_at":"2026-07-05T01:38:24.014960+00:00","updated_at":"2026-07-05T01:38:24.014960+00:00"}