{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RYUUOAK2ULJKPZ6DAKBCAFJ4UZ","short_pith_number":"pith:RYUUOAK2","schema_version":"1.0","canonical_sha256":"8e2947015aa2d2a7e7c3028220153ca662cd3c696224ea110bc5082cec19b5a5","source":{"kind":"arxiv","id":"2504.01250","version":2},"attestation_state":"computed","paper":{"title":"R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ian R. Manchester, Nicholas H. Barbara, Ruigang Wang","submitted_at":"2025-04-01T23:37:43Z","abstract_excerpt":"This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning and data-driven control. We construct R2DNs as the feedback interconnection of a linear time-invariant system and a 1-Lipschitz deep feedforward network, and directly parameterize the weights so that our models are stable (contracting) and robust to small input perturbations (Lipschitz) by design. Our parameterization uses a structure similar to the previously-proposed recurrent equilibrium network (REN), but without the requirement to iteratively s"},"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":"2504.01250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T23:37:43Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"280968eafb4378481178d869dc54e0146ba4807860fc00e1ccf461542d3270a8","abstract_canon_sha256":"17bbeaf237d753f521300c8dd1a06e5249a83a3a9d25ca9ea16727ab106b4b39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:04.264162Z","signature_b64":"c8+FEW20E44ohc3tYfgCteCgk2uMSP3EG0DjKdtGhzGRsN8a6htsmQmR+qOAB2PnCV3DGX35acYH7h7PaqCiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2947015aa2d2a7e7c3028220153ca662cd3c696224ea110bc5082cec19b5a5","last_reissued_at":"2026-06-03T01:05:04.263700Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:04.263700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ian R. Manchester, Nicholas H. Barbara, Ruigang Wang","submitted_at":"2025-04-01T23:37:43Z","abstract_excerpt":"This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning and data-driven control. We construct R2DNs as the feedback interconnection of a linear time-invariant system and a 1-Lipschitz deep feedforward network, and directly parameterize the weights so that our models are stable (contracting) and robust to small input perturbations (Lipschitz) by design. Our parameterization uses a structure similar to the previously-proposed recurrent equilibrium network (REN), but without the requirement to iteratively s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01250","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/2504.01250/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":"2504.01250","created_at":"2026-06-03T01:05:04.263761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01250v2","created_at":"2026-06-03T01:05:04.263761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01250","created_at":"2026-06-03T01:05:04.263761+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYUUOAK2ULJK","created_at":"2026-06-03T01:05:04.263761+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYUUOAK2ULJKPZ6D","created_at":"2026-06-03T01:05:04.263761+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYUUOAK2","created_at":"2026-06-03T01:05:04.263761+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/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ","json":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ.json","graph_json":"https://pith.science/api/pith-number/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/graph.json","events_json":"https://pith.science/api/pith-number/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/events.json","paper":"https://pith.science/paper/RYUUOAK2"},"agent_actions":{"view_html":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ","download_json":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ.json","view_paper":"https://pith.science/paper/RYUUOAK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01250&json=true","fetch_graph":"https://pith.science/api/pith-number/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/action/storage_attestation","attest_author":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/action/author_attestation","sign_citation":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/action/citation_signature","submit_replication":"https://pith.science/pith/RYUUOAK2ULJKPZ6DAKBCAFJ4UZ/action/replication_record"}},"created_at":"2026-06-03T01:05:04.263761+00:00","updated_at":"2026-06-03T01:05:04.263761+00:00"}