{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UX7OWBF54AOSBYSNFJHYB5JICA","short_pith_number":"pith:UX7OWBF5","schema_version":"1.0","canonical_sha256":"a5feeb04bde01d20e24d2a4f80f52810286242fd5d4b2c34557741c2dfb25bb3","source":{"kind":"arxiv","id":"2403.17793","version":1},"attestation_state":"computed","paper":{"title":"Neural Exponential Stabilization of Control-affine Nonlinear Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Giancarlo Ferrari-Trecate, Liang Xu, Muhammad Zakwan","submitted_at":"2024-03-26T15:27:24Z","abstract_excerpt":"This paper proposes a novel learning-based approach for achieving exponential stabilization of nonlinear control-affine systems. We leverage the Control Contraction Metrics (CCMs) framework to co-synthesize Neural Contraction Metrics (NCMs) and Neural Network (NN) controllers. First, we transform the infinite-dimensional semi-definite program (SDP) for CCM computation into a tractable inequality feasibility problem using element-wise bounds of matrix-valued functions. The terms in the inequality can be efficiently computed by our novel algorithms. Second, we propose a free parametrization of N"},"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":"2403.17793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-03-26T15:27:24Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"9361ee5060fb07e744b59804b5460b410c4b1723d14eed04de4807b75393b90e","abstract_canon_sha256":"e733f9b06e49a3cb306de4b4ca2c4d16203f45cad69a5498897feff732a28e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:55.417955Z","signature_b64":"OK9IbKyAOzFiNkyyuz1Mi17yXVS50rydteq46ebMddp9mWfZJNIMGGIFEYr/dPpaiWbNemUVk9pwmJtoPcH8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5feeb04bde01d20e24d2a4f80f52810286242fd5d4b2c34557741c2dfb25bb3","last_reissued_at":"2026-07-05T08:00:55.417520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:55.417520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Exponential Stabilization of Control-affine Nonlinear Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Giancarlo Ferrari-Trecate, Liang Xu, Muhammad Zakwan","submitted_at":"2024-03-26T15:27:24Z","abstract_excerpt":"This paper proposes a novel learning-based approach for achieving exponential stabilization of nonlinear control-affine systems. We leverage the Control Contraction Metrics (CCMs) framework to co-synthesize Neural Contraction Metrics (NCMs) and Neural Network (NN) controllers. First, we transform the infinite-dimensional semi-definite program (SDP) for CCM computation into a tractable inequality feasibility problem using element-wise bounds of matrix-valued functions. The terms in the inequality can be efficiently computed by our novel algorithms. Second, we propose a free parametrization of N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17793","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/2403.17793/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":"2403.17793","created_at":"2026-07-05T08:00:55.417578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17793v1","created_at":"2026-07-05T08:00:55.417578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17793","created_at":"2026-07-05T08:00:55.417578+00:00"},{"alias_kind":"pith_short_12","alias_value":"UX7OWBF54AOS","created_at":"2026-07-05T08:00:55.417578+00:00"},{"alias_kind":"pith_short_16","alias_value":"UX7OWBF54AOSBYSN","created_at":"2026-07-05T08:00:55.417578+00:00"},{"alias_kind":"pith_short_8","alias_value":"UX7OWBF5","created_at":"2026-07-05T08:00:55.417578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11432","citing_title":"Robust Convolution Neural ODEs via Contractivity-promoting regularization","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA","json":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA.json","graph_json":"https://pith.science/api/pith-number/UX7OWBF54AOSBYSNFJHYB5JICA/graph.json","events_json":"https://pith.science/api/pith-number/UX7OWBF54AOSBYSNFJHYB5JICA/events.json","paper":"https://pith.science/paper/UX7OWBF5"},"agent_actions":{"view_html":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA","download_json":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA.json","view_paper":"https://pith.science/paper/UX7OWBF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17793&json=true","fetch_graph":"https://pith.science/api/pith-number/UX7OWBF54AOSBYSNFJHYB5JICA/graph.json","fetch_events":"https://pith.science/api/pith-number/UX7OWBF54AOSBYSNFJHYB5JICA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA/action/storage_attestation","attest_author":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA/action/author_attestation","sign_citation":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA/action/citation_signature","submit_replication":"https://pith.science/pith/UX7OWBF54AOSBYSNFJHYB5JICA/action/replication_record"}},"created_at":"2026-07-05T08:00:55.417578+00:00","updated_at":"2026-07-05T08:00:55.417578+00:00"}