{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7CMEMXWO7E6GMRQHHH232QLGLX","short_pith_number":"pith:7CMEMXWO","schema_version":"1.0","canonical_sha256":"f898465ecef93c66460739f5bd41665dc8c5c0abc03bd267057960349a2c03f7","source":{"kind":"arxiv","id":"1905.05894","version":3},"attestation_state":"computed","paper":{"title":"Online Normalization for Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Atli Kosson, Ilya Sharapov, Michael James, Ryan Reece, Sofia Samaniego de la Fuente, Urs Koster, Vishal Subbiah, Vitaliy Chiley","submitted_at":"2019-05-15T00:09:29Z","abstract_excerpt":"Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as accurate as Batch Normalization. We resolve a theoretical limitation of Batch Normalization by introducing an unbiased technique for computing the gradient of normalized activations. Online Normalization works with automatic differentiation by adding statistical normalization as a primitive. This technique can be used in cases not covered by some other normalizers, such as recu"},"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":"1905.05894","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T00:09:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"258f47a92f301316a8fc2178fa416add86e4cb0395c003fa3b9225880642381c","abstract_canon_sha256":"fd0f1c6fcd9f0642eb24bfd67a73ae0d8ec74430c89adb39f0df7675f6e8f05d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:49.448189Z","signature_b64":"lcrV7H7JmJoOW/uIhZsDRfEsWmBrd9KlQ12QUxXXVKNvvB9p4VS29g+r26xxauQaBGxixQkktqJdbcD6DOPDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f898465ecef93c66460739f5bd41665dc8c5c0abc03bd267057960349a2c03f7","last_reissued_at":"2026-07-05T00:23:49.447628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:49.447628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Normalization for Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Atli Kosson, Ilya Sharapov, Michael James, Ryan Reece, Sofia Samaniego de la Fuente, Urs Koster, Vishal Subbiah, Vitaliy Chiley","submitted_at":"2019-05-15T00:09:29Z","abstract_excerpt":"Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as accurate as Batch Normalization. We resolve a theoretical limitation of Batch Normalization by introducing an unbiased technique for computing the gradient of normalized activations. Online Normalization works with automatic differentiation by adding statistical normalization as a primitive. This technique can be used in cases not covered by some other normalizers, such as recu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05894","kind":"arxiv","version":3},"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/1905.05894/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":"1905.05894","created_at":"2026-07-05T00:23:49.447686+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05894v3","created_at":"2026-07-05T00:23:49.447686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05894","created_at":"2026-07-05T00:23:49.447686+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CMEMXWO7E6G","created_at":"2026-07-05T00:23:49.447686+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CMEMXWO7E6GMRQH","created_at":"2026-07-05T00:23:49.447686+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CMEMXWO","created_at":"2026-07-05T00:23:49.447686+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/7CMEMXWO7E6GMRQHHH232QLGLX","json":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX.json","graph_json":"https://pith.science/api/pith-number/7CMEMXWO7E6GMRQHHH232QLGLX/graph.json","events_json":"https://pith.science/api/pith-number/7CMEMXWO7E6GMRQHHH232QLGLX/events.json","paper":"https://pith.science/paper/7CMEMXWO"},"agent_actions":{"view_html":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX","download_json":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX.json","view_paper":"https://pith.science/paper/7CMEMXWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05894&json=true","fetch_graph":"https://pith.science/api/pith-number/7CMEMXWO7E6GMRQHHH232QLGLX/graph.json","fetch_events":"https://pith.science/api/pith-number/7CMEMXWO7E6GMRQHHH232QLGLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX/action/storage_attestation","attest_author":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX/action/author_attestation","sign_citation":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX/action/citation_signature","submit_replication":"https://pith.science/pith/7CMEMXWO7E6GMRQHHH232QLGLX/action/replication_record"}},"created_at":"2026-07-05T00:23:49.447686+00:00","updated_at":"2026-07-05T00:23:49.447686+00:00"}