{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5NWQHYCSP64JBYXD7D5NJP7GCB","short_pith_number":"pith:5NWQHYCS","schema_version":"1.0","canonical_sha256":"eb6d03e0527fb890e2e3f8fad4bfe610760e0d841902d79bf596c425dbf8435e","source":{"kind":"arxiv","id":"2506.23977","version":1},"attestation_state":"computed","paper":{"title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ming Jin, Vassilis Kekatos, Zain ul Abdeen","submitted_at":"2025-06-30T15:42:23Z","abstract_excerpt":"Certified robustness is a critical property for deploying neural networks (NN) in safety-critical applications. A principle approach to achieving such guarantees is to constrain the global Lipschitz constant of the network. However, accurate methods for Lipschitz-constrained training often suffer from non-convex formulations and poor scalability due to reliance on global semidefinite programs (SDPs). In this letter, we propose a convex training framework that enforces global Lipschitz constraints via semidefinite relaxation. By reparameterizing the NN using loop transformation, we derive a con"},"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":"2506.23977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T15:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"3b14c5ee29fabb6d759dcd54e840f7dc024f585089e0ad481a56503895b85f1f","abstract_canon_sha256":"b0e022ae70d89c8ddba242c72dc126b9d804f1c8ea1474ee05e0f7535f1cd4a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:31.042701Z","signature_b64":"qDGa/Lej6hC5TSqSPsWVwlQAS/JIRFL2cmmmJlOXazs3aYU1dDsSf1lmENlq1z7FBoyyK6pCBtjJV67wcVIeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb6d03e0527fb890e2e3f8fad4bfe610760e0d841902d79bf596c425dbf8435e","last_reissued_at":"2026-07-05T11:29:31.042206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:31.042206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ming Jin, Vassilis Kekatos, Zain ul Abdeen","submitted_at":"2025-06-30T15:42:23Z","abstract_excerpt":"Certified robustness is a critical property for deploying neural networks (NN) in safety-critical applications. A principle approach to achieving such guarantees is to constrain the global Lipschitz constant of the network. However, accurate methods for Lipschitz-constrained training often suffer from non-convex formulations and poor scalability due to reliance on global semidefinite programs (SDPs). In this letter, we propose a convex training framework that enforces global Lipschitz constraints via semidefinite relaxation. By reparameterizing the NN using loop transformation, we derive a con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23977","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.23977/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":"2506.23977","created_at":"2026-07-05T11:29:31.042257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23977v1","created_at":"2026-07-05T11:29:31.042257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23977","created_at":"2026-07-05T11:29:31.042257+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NWQHYCSP64J","created_at":"2026-07-05T11:29:31.042257+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NWQHYCSP64JBYXD","created_at":"2026-07-05T11:29:31.042257+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NWQHYCS","created_at":"2026-07-05T11:29:31.042257+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/5NWQHYCSP64JBYXD7D5NJP7GCB","json":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB.json","graph_json":"https://pith.science/api/pith-number/5NWQHYCSP64JBYXD7D5NJP7GCB/graph.json","events_json":"https://pith.science/api/pith-number/5NWQHYCSP64JBYXD7D5NJP7GCB/events.json","paper":"https://pith.science/paper/5NWQHYCS"},"agent_actions":{"view_html":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB","download_json":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB.json","view_paper":"https://pith.science/paper/5NWQHYCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23977&json=true","fetch_graph":"https://pith.science/api/pith-number/5NWQHYCSP64JBYXD7D5NJP7GCB/graph.json","fetch_events":"https://pith.science/api/pith-number/5NWQHYCSP64JBYXD7D5NJP7GCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB/action/storage_attestation","attest_author":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB/action/author_attestation","sign_citation":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB/action/citation_signature","submit_replication":"https://pith.science/pith/5NWQHYCSP64JBYXD7D5NJP7GCB/action/replication_record"}},"created_at":"2026-07-05T11:29:31.042257+00:00","updated_at":"2026-07-05T11:29:31.042257+00:00"}