{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VQDQKYLAMIYWORJRPXJIJUBGAY","short_pith_number":"pith:VQDQKYLA","schema_version":"1.0","canonical_sha256":"ac0705616062316745317dd284d026062f9a7c20c24bce60fc706e0f44d4135f","source":{"kind":"arxiv","id":"1907.10473","version":1},"attestation_state":"computed","paper":{"title":"Switchable Normalization for Learning-to-Normalize Deep Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiamin Ren, Jingyu Li, Ping Luo, Ruimao Zhang, Zhanglin Peng","submitted_at":"2019-07-22T17:50:31Z","abstract_excerpt":"We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. SN employs three distinct scopes to compute statistics (means and variances) including a channel, a layer, and a minibatch. SN switches between them by learning their importance weights in an end-to-end manner. It has several good properties. First, it adapts to various network architectures and tasks. Second, it is robust to a wide range of batch sizes, maintaining high performance even when small minib"},"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":"1907.10473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-22T17:50:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"02b177b6b85e430253fdc090caa4b7fa070bd0c8570d8d2c79190490363e5c42","abstract_canon_sha256":"d425810fee98d9a9bc89b58d0a8f7db2aa467493c1aa79bfdf8859fcd3cda136"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:37.821510Z","signature_b64":"/k0mtA8iMKoO+Kf2wLe703uuCi8aSSwgofhQR1JCM4f7bIUe9GvV7Niwkc9xxvh3x+Vy0dfJjfBhMLFVTKiiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac0705616062316745317dd284d026062f9a7c20c24bce60fc706e0f44d4135f","last_reissued_at":"2026-05-17T23:39:37.820906Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:37.820906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Switchable Normalization for Learning-to-Normalize Deep Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiamin Ren, Jingyu Li, Ping Luo, Ruimao Zhang, Zhanglin Peng","submitted_at":"2019-07-22T17:50:31Z","abstract_excerpt":"We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network. SN employs three distinct scopes to compute statistics (means and variances) including a channel, a layer, and a minibatch. SN switches between them by learning their importance weights in an end-to-end manner. It has several good properties. First, it adapts to various network architectures and tasks. Second, it is robust to a wide range of batch sizes, maintaining high performance even when small minib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10473","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":""},"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":"1907.10473","created_at":"2026-05-17T23:39:37.820992+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.10473v1","created_at":"2026-05-17T23:39:37.820992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10473","created_at":"2026-05-17T23:39:37.820992+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQDQKYLAMIYW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQDQKYLAMIYWORJR","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQDQKYLA","created_at":"2026-05-18T12:33:30.264802+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/VQDQKYLAMIYWORJRPXJIJUBGAY","json":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY.json","graph_json":"https://pith.science/api/pith-number/VQDQKYLAMIYWORJRPXJIJUBGAY/graph.json","events_json":"https://pith.science/api/pith-number/VQDQKYLAMIYWORJRPXJIJUBGAY/events.json","paper":"https://pith.science/paper/VQDQKYLA"},"agent_actions":{"view_html":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY","download_json":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY.json","view_paper":"https://pith.science/paper/VQDQKYLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.10473&json=true","fetch_graph":"https://pith.science/api/pith-number/VQDQKYLAMIYWORJRPXJIJUBGAY/graph.json","fetch_events":"https://pith.science/api/pith-number/VQDQKYLAMIYWORJRPXJIJUBGAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY/action/storage_attestation","attest_author":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY/action/author_attestation","sign_citation":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY/action/citation_signature","submit_replication":"https://pith.science/pith/VQDQKYLAMIYWORJRPXJIJUBGAY/action/replication_record"}},"created_at":"2026-05-17T23:39:37.820992+00:00","updated_at":"2026-05-17T23:39:37.820992+00:00"}