{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TWXZ2OW2Q2UUIFT3IZVQPKQKJ4","short_pith_number":"pith:TWXZ2OW2","schema_version":"1.0","canonical_sha256":"9daf9d3ada86a944167b466b07aa0a4f2e18cb4b42089377a02df4119a209935","source":{"kind":"arxiv","id":"1809.01129","version":1},"attestation_state":"computed","paper":{"title":"Lipschitz Networks and Distributional Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Richard Nock, Simon Kornblith, Zac Cranko, Zhan Shi","submitted_at":"2018-09-04T03:12:40Z","abstract_excerpt":"Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class rich enough to include deep neural networks by a regularised empirical risk involving the Lipschitz constant of the model. This allows us to interpretand quantify the robustness properties of a deep neural network. As an application we show the distributionally robust risk upperbounds the adversarial training risk."},"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":"1809.01129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-04T03:12:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00a06660b0c1b4f18beba826ef32e99d6a1b1cdaf35c7062dd71d085d47d3a2a","abstract_canon_sha256":"59b1d689ca0be813b848675c493d469a8750787492ab630e18f2d9deb15965f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:31.482182Z","signature_b64":"/Fdi5HQmL35GE7s3crlQacg7cOOvahQJW1orGiYiBHlVGY9P3gU+SMUbqmaGXv89xyEtURWAylIIy81SrUYnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9daf9d3ada86a944167b466b07aa0a4f2e18cb4b42089377a02df4119a209935","last_reissued_at":"2026-05-18T00:06:31.481724Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:31.481724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lipschitz Networks and Distributional Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Richard Nock, Simon Kornblith, Zac Cranko, Zhan Shi","submitted_at":"2018-09-04T03:12:40Z","abstract_excerpt":"Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class rich enough to include deep neural networks by a regularised empirical risk involving the Lipschitz constant of the model. This allows us to interpretand quantify the robustness properties of a deep neural network. As an application we show the distributionally robust risk upperbounds the adversarial training risk."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01129","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":"1809.01129","created_at":"2026-05-18T00:06:31.481797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01129v1","created_at":"2026-05-18T00:06:31.481797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01129","created_at":"2026-05-18T00:06:31.481797+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWXZ2OW2Q2UU","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWXZ2OW2Q2UUIFT3","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWXZ2OW2","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07925","citing_title":"Sinkhorn doubly stochastic attention rank decay analysis","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4","json":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4.json","graph_json":"https://pith.science/api/pith-number/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/graph.json","events_json":"https://pith.science/api/pith-number/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/events.json","paper":"https://pith.science/paper/TWXZ2OW2"},"agent_actions":{"view_html":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4","download_json":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4.json","view_paper":"https://pith.science/paper/TWXZ2OW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01129&json=true","fetch_graph":"https://pith.science/api/pith-number/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/action/storage_attestation","attest_author":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/action/author_attestation","sign_citation":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/action/citation_signature","submit_replication":"https://pith.science/pith/TWXZ2OW2Q2UUIFT3IZVQPKQKJ4/action/replication_record"}},"created_at":"2026-05-18T00:06:31.481797+00:00","updated_at":"2026-05-18T00:06:31.481797+00:00"}