{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D6FA2VLYRWDN2P4TWBHONYNEFG","short_pith_number":"pith:D6FA2VLY","schema_version":"1.0","canonical_sha256":"1f8a0d55788d86dd3f93b04ee6e1a429a877ecfc48821dc6ebf11444f36e3264","source":{"kind":"arxiv","id":"2408.15456","version":3},"attestation_state":"computed","paper":{"title":"Convergence Analysis of Gradient Flow for Overparameterized LQR Formulations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","math.DS"],"primary_cat":"eess.SY","authors_text":"Arthur Castello B. de Oliveira, Eduardo D. Sontag, Milad Siami","submitted_at":"2024-08-28T00:30:37Z","abstract_excerpt":"Motivated by the growing use of artificial intelligence (AI) tools in control design, this paper analyses the intersection between results from gradient methods for the model-free linear quadratic regulator (LQR), and linear feedforward neural networks (LFFNNs), More specifically, it looks into the case where one wants to find a LFFNN feedback that minimizes a LQR cost. This paper starts by analyzing the structure of the gradient expression for the parameters of each layer, which implies a key conservation law of the system. This conservation law is then leveraged to generalize existing result"},"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":"2408.15456","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.SY","submitted_at":"2024-08-28T00:30:37Z","cross_cats_sorted":["cs.SY","math.DS"],"title_canon_sha256":"47bb9ced66cdd1b1cb2d2242ca8e1d1bc1748851b15070c11111b04de0a38db0","abstract_canon_sha256":"d1e91996a5d1aae079dff0a6e8aa55e3110acbf3fb301cd3ba00ab46c63047e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:43.190670Z","signature_b64":"nOU+veosZ9dRqcC85jIZqWnidqhLBIFykBLej3WTsTjlKrH2hL3HGkLFrhBWcoZsqs9Yfu9PsPlpTWOAnzZRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f8a0d55788d86dd3f93b04ee6e1a429a877ecfc48821dc6ebf11444f36e3264","last_reissued_at":"2026-07-05T11:09:43.190169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:43.190169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Analysis of Gradient Flow for Overparameterized LQR Formulations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","math.DS"],"primary_cat":"eess.SY","authors_text":"Arthur Castello B. de Oliveira, Eduardo D. Sontag, Milad Siami","submitted_at":"2024-08-28T00:30:37Z","abstract_excerpt":"Motivated by the growing use of artificial intelligence (AI) tools in control design, this paper analyses the intersection between results from gradient methods for the model-free linear quadratic regulator (LQR), and linear feedforward neural networks (LFFNNs), More specifically, it looks into the case where one wants to find a LFFNN feedback that minimizes a LQR cost. This paper starts by analyzing the structure of the gradient expression for the parameters of each layer, which implies a key conservation law of the system. This conservation law is then leveraged to generalize existing result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15456","kind":"arxiv","version":3},"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/2408.15456/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":"2408.15456","created_at":"2026-07-05T11:09:43.190226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15456v3","created_at":"2026-07-05T11:09:43.190226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15456","created_at":"2026-07-05T11:09:43.190226+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6FA2VLYRWDN","created_at":"2026-07-05T11:09:43.190226+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6FA2VLYRWDN2P4T","created_at":"2026-07-05T11:09:43.190226+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6FA2VLY","created_at":"2026-07-05T11:09:43.190226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06134","citing_title":"Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Time Scales","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG","json":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG.json","graph_json":"https://pith.science/api/pith-number/D6FA2VLYRWDN2P4TWBHONYNEFG/graph.json","events_json":"https://pith.science/api/pith-number/D6FA2VLYRWDN2P4TWBHONYNEFG/events.json","paper":"https://pith.science/paper/D6FA2VLY"},"agent_actions":{"view_html":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG","download_json":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG.json","view_paper":"https://pith.science/paper/D6FA2VLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15456&json=true","fetch_graph":"https://pith.science/api/pith-number/D6FA2VLYRWDN2P4TWBHONYNEFG/graph.json","fetch_events":"https://pith.science/api/pith-number/D6FA2VLYRWDN2P4TWBHONYNEFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG/action/storage_attestation","attest_author":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG/action/author_attestation","sign_citation":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG/action/citation_signature","submit_replication":"https://pith.science/pith/D6FA2VLYRWDN2P4TWBHONYNEFG/action/replication_record"}},"created_at":"2026-07-05T11:09:43.190226+00:00","updated_at":"2026-07-05T11:09:43.190226+00:00"}