{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SIGUNBWL4R7FHX74IO4HY4524H","short_pith_number":"pith:SIGUNBWL","schema_version":"1.0","canonical_sha256":"920d4686cbe47e53dffc43b87c73bae1cd9ef25643c7a7c8c79704383bb1c4cd","source":{"kind":"arxiv","id":"1705.10941","version":1},"attestation_state":"computed","paper":{"title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Takeru Miyato, Yuichi Yoshida","submitted_at":"2017-05-31T04:56:25Z","abstract_excerpt":"We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to perturbation, we propose a simple and effective regularization method, referred to as spectral norm regularization, which penalizes the high spectral norm of weight matrices in neural networks. We provide supportive evidence for the abovementioned hypothesis by experimentally confirming that the models trained using spectral norm regularization exhibit better general"},"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":"1705.10941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-31T04:56:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"493ccb98b119ac5be8e5dc23f3531fdc8490c84a93f0d1640bb9346211094879","abstract_canon_sha256":"977d21d4a0a3ae165f9545f3d8eefa1a58fd284ebd6b6e25544aade43759420b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:19.791571Z","signature_b64":"w4HxP9Pj6f5Ru5uim2GD065PK6dJMlVZZ3m9UUiIEC8EuuiZSUg3dGEL6ZHZS/gbMxHFtzhcaeUr6o4RqfEJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"920d4686cbe47e53dffc43b87c73bae1cd9ef25643c7a7c8c79704383bb1c4cd","last_reissued_at":"2026-05-18T00:43:19.790952Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:19.790952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Takeru Miyato, Yuichi Yoshida","submitted_at":"2017-05-31T04:56:25Z","abstract_excerpt":"We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to perturbation, we propose a simple and effective regularization method, referred to as spectral norm regularization, which penalizes the high spectral norm of weight matrices in neural networks. We provide supportive evidence for the abovementioned hypothesis by experimentally confirming that the models trained using spectral norm regularization exhibit better general"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10941","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":"1705.10941","created_at":"2026-05-18T00:43:19.791044+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.10941v1","created_at":"2026-05-18T00:43:19.791044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10941","created_at":"2026-05-18T00:43:19.791044+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIGUNBWL4R7F","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIGUNBWL4R7FHX74","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIGUNBWL","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1906.10654","citing_title":"ReachNN: Reachability Analysis of Neural-Network Controlled Systems","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04003","citing_title":"Mean Spectral Normalization of Deep Neural Networks for Embedded Automation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2510.07195","citing_title":"Accelerating Inference for Multilayer Neural Networks with Quantum Computers","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16134","citing_title":"Navigating Potholes with Geometry-Aware Sharpness Minimization","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19425","citing_title":"When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15416","citing_title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09742","citing_title":"Upper Generalization Bounds for Neural Oscillators","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04030","citing_title":"Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12492","citing_title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18907","citing_title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H","json":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H.json","graph_json":"https://pith.science/api/pith-number/SIGUNBWL4R7FHX74IO4HY4524H/graph.json","events_json":"https://pith.science/api/pith-number/SIGUNBWL4R7FHX74IO4HY4524H/events.json","paper":"https://pith.science/paper/SIGUNBWL"},"agent_actions":{"view_html":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H","download_json":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H.json","view_paper":"https://pith.science/paper/SIGUNBWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.10941&json=true","fetch_graph":"https://pith.science/api/pith-number/SIGUNBWL4R7FHX74IO4HY4524H/graph.json","fetch_events":"https://pith.science/api/pith-number/SIGUNBWL4R7FHX74IO4HY4524H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H/action/storage_attestation","attest_author":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H/action/author_attestation","sign_citation":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H/action/citation_signature","submit_replication":"https://pith.science/pith/SIGUNBWL4R7FHX74IO4HY4524H/action/replication_record"}},"created_at":"2026-05-18T00:43:19.791044+00:00","updated_at":"2026-05-18T00:43:19.791044+00:00"}