{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TAC5VXB7XY25K6MS3J7VDFASP4","short_pith_number":"pith:TAC5VXB7","schema_version":"1.0","canonical_sha256":"9805dadc3fbe35d57992da7f5194127f2cd50fe07ab6eb016c8ff2377509cefc","source":{"kind":"arxiv","id":"1906.04893","version":2},"attestation_state":"computed","paper":{"title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Robey, George J. Pappas, Hamed Hassani, Mahyar Fazlyab, Manfred Morari","submitted_at":"2019-06-12T02:18:19Z","abstract_excerpt":"Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis of closed-loop systems with reinforcement learning controllers. Existing methods in the literature for estimating the Lipschitz constant suffer from either lack of accuracy or poor scalability. In this paper, we present a convex optimization framework to compute guaranteed upper bounds on the Lipschitz constant of DNNs both accurately and efficiently. Our main idea is to interpret activation functions as gradients o"},"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":"1906.04893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T02:18:19Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"89c47d832df06c9a425065f2e2922c11a9391c23099ce5c8d86f7e7b0fd5063c","abstract_canon_sha256":"b47b5a9c70f239aba926a1c3435959f7d08095a3e296f307bffe86ad0dcc261c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:02.559493Z","signature_b64":"xHNRFq2YuVt9ixCimRhCjRlKn9VtT2/R43KM1epMWSkHjUHIAY/aD32D/fDEvwjRB+/WBOs68y3WpFXE8gqIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9805dadc3fbe35d57992da7f5194127f2cd50fe07ab6eb016c8ff2377509cefc","last_reissued_at":"2026-07-05T05:33:02.559042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:02.559042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Robey, George J. Pappas, Hamed Hassani, Mahyar Fazlyab, Manfred Morari","submitted_at":"2019-06-12T02:18:19Z","abstract_excerpt":"Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis of closed-loop systems with reinforcement learning controllers. Existing methods in the literature for estimating the Lipschitz constant suffer from either lack of accuracy or poor scalability. In this paper, we present a convex optimization framework to compute guaranteed upper bounds on the Lipschitz constant of DNNs both accurately and efficiently. Our main idea is to interpret activation functions as gradients o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04893","kind":"arxiv","version":2},"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/1906.04893/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":"1906.04893","created_at":"2026-07-05T05:33:02.559106+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04893v2","created_at":"2026-07-05T05:33:02.559106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04893","created_at":"2026-07-05T05:33:02.559106+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAC5VXB7XY25","created_at":"2026-07-05T05:33:02.559106+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAC5VXB7XY25K6MS","created_at":"2026-07-05T05:33:02.559106+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAC5VXB7","created_at":"2026-07-05T05:33:02.559106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15238","citing_title":"A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4","json":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4.json","graph_json":"https://pith.science/api/pith-number/TAC5VXB7XY25K6MS3J7VDFASP4/graph.json","events_json":"https://pith.science/api/pith-number/TAC5VXB7XY25K6MS3J7VDFASP4/events.json","paper":"https://pith.science/paper/TAC5VXB7"},"agent_actions":{"view_html":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4","download_json":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4.json","view_paper":"https://pith.science/paper/TAC5VXB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04893&json=true","fetch_graph":"https://pith.science/api/pith-number/TAC5VXB7XY25K6MS3J7VDFASP4/graph.json","fetch_events":"https://pith.science/api/pith-number/TAC5VXB7XY25K6MS3J7VDFASP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4/action/storage_attestation","attest_author":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4/action/author_attestation","sign_citation":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4/action/citation_signature","submit_replication":"https://pith.science/pith/TAC5VXB7XY25K6MS3J7VDFASP4/action/replication_record"}},"created_at":"2026-07-05T05:33:02.559106+00:00","updated_at":"2026-07-05T05:33:02.559106+00:00"}