{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ONXHD6WNVXQMS2ZG7P5E2UGC4C","short_pith_number":"pith:ONXHD6WN","schema_version":"1.0","canonical_sha256":"736e71facdade0c96b26fbfa4d50c2e09dcef73b3ab6b2c668c00f3760f99953","source":{"kind":"arxiv","id":"1603.01431","version":6},"attestation_state":"computed","paper":{"title":"Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bhargava U. Kota, Devansh Arpit, Venu Govindaraju, Yingbo Zhou","submitted_at":"2016-03-04T12:01:58Z","abstract_excerpt":"While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics for layerwise input normalization during training which makes the estimates of mean and standard deviation of input (distribution) to hidden layers inaccurate for validation due to shifting parameter values (especially during initial training epochs). Also, BN cannot be used with batch-size 1 during training. We address these drawbacks by proposing a non-ad"},"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":"1603.01431","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-03-04T12:01:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bcdb561d8a35579025afdf870fa37ed5cfe00476996727861c55a9ac1a31a626","abstract_canon_sha256":"76865838c5ae84f8dde0b2ff7ab27eef25c5e65beb616f1eb88394961fcb285c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:12.584485Z","signature_b64":"qWO2CRVTd7nXFbxsuribQeHfGMVYEgFIG0rkF6uVsuqPNe+g1OCY8jrtWNAXxqFGW5JyEHwniFXf70GGf33SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"736e71facdade0c96b26fbfa4d50c2e09dcef73b3ab6b2c668c00f3760f99953","last_reissued_at":"2026-05-18T01:11:12.584034Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:12.584034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bhargava U. Kota, Devansh Arpit, Venu Govindaraju, Yingbo Zhou","submitted_at":"2016-03-04T12:01:58Z","abstract_excerpt":"While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics for layerwise input normalization during training which makes the estimates of mean and standard deviation of input (distribution) to hidden layers inaccurate for validation due to shifting parameter values (especially during initial training epochs). Also, BN cannot be used with batch-size 1 during training. We address these drawbacks by proposing a non-ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.01431","kind":"arxiv","version":6},"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":"1603.01431","created_at":"2026-05-18T01:11:12.584113+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.01431v6","created_at":"2026-05-18T01:11:12.584113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01431","created_at":"2026-05-18T01:11:12.584113+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONXHD6WNVXQM","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONXHD6WNVXQMS2ZG","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONXHD6WN","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C","json":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C.json","graph_json":"https://pith.science/api/pith-number/ONXHD6WNVXQMS2ZG7P5E2UGC4C/graph.json","events_json":"https://pith.science/api/pith-number/ONXHD6WNVXQMS2ZG7P5E2UGC4C/events.json","paper":"https://pith.science/paper/ONXHD6WN"},"agent_actions":{"view_html":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C","download_json":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C.json","view_paper":"https://pith.science/paper/ONXHD6WN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.01431&json=true","fetch_graph":"https://pith.science/api/pith-number/ONXHD6WNVXQMS2ZG7P5E2UGC4C/graph.json","fetch_events":"https://pith.science/api/pith-number/ONXHD6WNVXQMS2ZG7P5E2UGC4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C/action/storage_attestation","attest_author":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C/action/author_attestation","sign_citation":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C/action/citation_signature","submit_replication":"https://pith.science/pith/ONXHD6WNVXQMS2ZG7P5E2UGC4C/action/replication_record"}},"created_at":"2026-05-18T01:11:12.584113+00:00","updated_at":"2026-05-18T01:11:12.584113+00:00"}