{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3UZHFOK2WW5IDJ2AILTHZ3H544","short_pith_number":"pith:3UZHFOK2","schema_version":"1.0","canonical_sha256":"dd3272b95ab5ba81a74042e67cecfde711680958e1ca3a5f7285d3faa67fe46c","source":{"kind":"arxiv","id":"2404.07373","version":2},"attestation_state":"computed","paper":{"title":"Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Murat Arcak, Neelay Junnarkar, Peter Seiler","submitted_at":"2024-04-10T22:15:28Z","abstract_excerpt":"This paper presents a method to synthesize neural network controllers to maximize reward subject to the hard constraint that the feedback system of plant and controller be dissipative, certifying requirements such as stability and $L_2$ gain bounds. It considers nonlinear and uncertain plants, modeled as the interconnection of a linear time-invariant (LTI) system and an uncertainty block, which incorporates nonlinearities. The uncertainty of the plant and the activation functions of the neural network are both described using integral quadratic constraints (IQCs). First, a dissipativity condit"},"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":"2404.07373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-04-10T22:15:28Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"c833e15d5199337cbccf32286c25914986d4172cb92c3de60528547873d0a566","abstract_canon_sha256":"5fe6c9196382e4d26203730ae03c17837acf122038f0ea70f2047d090ad68afb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:28.521821Z","signature_b64":"EcHeYYi8eXatXYyvOwWS0c5rS6qUdjhGMbTZ8G/igkFoTP6riEiYRAWJ7ZwSvJrTpBS+UcJCH9Yrns5yyPMdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3272b95ab5ba81a74042e67cecfde711680958e1ca3a5f7285d3faa67fe46c","last_reissued_at":"2026-06-02T01:03:28.521328Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:28.521328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Murat Arcak, Neelay Junnarkar, Peter Seiler","submitted_at":"2024-04-10T22:15:28Z","abstract_excerpt":"This paper presents a method to synthesize neural network controllers to maximize reward subject to the hard constraint that the feedback system of plant and controller be dissipative, certifying requirements such as stability and $L_2$ gain bounds. It considers nonlinear and uncertain plants, modeled as the interconnection of a linear time-invariant (LTI) system and an uncertainty block, which incorporates nonlinearities. The uncertainty of the plant and the activation functions of the neural network are both described using integral quadratic constraints (IQCs). First, a dissipativity condit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07373","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/2404.07373/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":"2404.07373","created_at":"2026-06-02T01:03:28.521385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07373v2","created_at":"2026-06-02T01:03:28.521385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07373","created_at":"2026-06-02T01:03:28.521385+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UZHFOK2WW5I","created_at":"2026-06-02T01:03:28.521385+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UZHFOK2WW5IDJ2A","created_at":"2026-06-02T01:03:28.521385+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UZHFOK2","created_at":"2026-06-02T01:03:28.521385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18292","citing_title":"Learning the dynamics of nonlinear systems with regional stability guarantees through linear matrix inequality constraints","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544","json":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544.json","graph_json":"https://pith.science/api/pith-number/3UZHFOK2WW5IDJ2AILTHZ3H544/graph.json","events_json":"https://pith.science/api/pith-number/3UZHFOK2WW5IDJ2AILTHZ3H544/events.json","paper":"https://pith.science/paper/3UZHFOK2"},"agent_actions":{"view_html":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544","download_json":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544.json","view_paper":"https://pith.science/paper/3UZHFOK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07373&json=true","fetch_graph":"https://pith.science/api/pith-number/3UZHFOK2WW5IDJ2AILTHZ3H544/graph.json","fetch_events":"https://pith.science/api/pith-number/3UZHFOK2WW5IDJ2AILTHZ3H544/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544/action/storage_attestation","attest_author":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544/action/author_attestation","sign_citation":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544/action/citation_signature","submit_replication":"https://pith.science/pith/3UZHFOK2WW5IDJ2AILTHZ3H544/action/replication_record"}},"created_at":"2026-06-02T01:03:28.521385+00:00","updated_at":"2026-06-02T01:03:28.521385+00:00"}