{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S7AU73IGLOEZW2DAVBPC7UFSYQ","short_pith_number":"pith:S7AU73IG","schema_version":"1.0","canonical_sha256":"97c14fed065b899b6860a85e2fd0b2c43d73ec272db5eab869ce6d142b2bb8e7","source":{"kind":"arxiv","id":"2205.10089","version":4},"attestation_state":"computed","paper":{"title":"Kernel Normalized Convolutional Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Rueckert, Georgios Kaissis, Reihaneh Torkzadehmahani, Reza Nasirigerdeh","submitted_at":"2022-05-20T11:18:05Z","abstract_excerpt":"Existing convolutional neural network architectures frequently rely upon batch normalization (BatchNorm) to effectively train the model. BatchNorm, however, performs poorly with small batch sizes, and is inapplicable to differential privacy. To address these limitations, we propose the kernel normalization (KernelNorm) and kernel normalized convolutional layers, and incorporate them into kernel normalized convolutional networks (KNConvNets) as the main building blocks. We implement KNConvNets corresponding to the state-of-the-art ResNets while forgoing the BatchNorm layers. Through extensive e"},"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":"2205.10089","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T11:18:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7ed84330d370c141e247b3fa2bdab8aedebfd9cb1cb5bf3fa741e009919e4416","abstract_canon_sha256":"7bde62d64c17943676afea920a7142c53509ecc086baf09c354f12f065b111c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:59.671273Z","signature_b64":"vi91zEhowO58Hq+vgmCAfMAN+4c4MKUyDf0mIkN7qepEixK85+Ct4lWHA4IdYqVSZajlaqjK8leb0HraPZesAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c14fed065b899b6860a85e2fd0b2c43d73ec272db5eab869ce6d142b2bb8e7","last_reissued_at":"2026-07-05T07:51:59.670843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:59.670843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel Normalized Convolutional Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Rueckert, Georgios Kaissis, Reihaneh Torkzadehmahani, Reza Nasirigerdeh","submitted_at":"2022-05-20T11:18:05Z","abstract_excerpt":"Existing convolutional neural network architectures frequently rely upon batch normalization (BatchNorm) to effectively train the model. BatchNorm, however, performs poorly with small batch sizes, and is inapplicable to differential privacy. To address these limitations, we propose the kernel normalization (KernelNorm) and kernel normalized convolutional layers, and incorporate them into kernel normalized convolutional networks (KNConvNets) as the main building blocks. We implement KNConvNets corresponding to the state-of-the-art ResNets while forgoing the BatchNorm layers. Through extensive e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10089","kind":"arxiv","version":4},"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/2205.10089/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":"2205.10089","created_at":"2026-07-05T07:51:59.670897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10089v4","created_at":"2026-07-05T07:51:59.670897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10089","created_at":"2026-07-05T07:51:59.670897+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7AU73IGLOEZ","created_at":"2026-07-05T07:51:59.670897+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7AU73IGLOEZW2DA","created_at":"2026-07-05T07:51:59.670897+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7AU73IG","created_at":"2026-07-05T07:51:59.670897+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/S7AU73IGLOEZW2DAVBPC7UFSYQ","json":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ.json","graph_json":"https://pith.science/api/pith-number/S7AU73IGLOEZW2DAVBPC7UFSYQ/graph.json","events_json":"https://pith.science/api/pith-number/S7AU73IGLOEZW2DAVBPC7UFSYQ/events.json","paper":"https://pith.science/paper/S7AU73IG"},"agent_actions":{"view_html":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ","download_json":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ.json","view_paper":"https://pith.science/paper/S7AU73IG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10089&json=true","fetch_graph":"https://pith.science/api/pith-number/S7AU73IGLOEZW2DAVBPC7UFSYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/S7AU73IGLOEZW2DAVBPC7UFSYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ/action/storage_attestation","attest_author":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ/action/author_attestation","sign_citation":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ/action/citation_signature","submit_replication":"https://pith.science/pith/S7AU73IGLOEZW2DAVBPC7UFSYQ/action/replication_record"}},"created_at":"2026-07-05T07:51:59.670897+00:00","updated_at":"2026-07-05T07:51:59.670897+00:00"}