{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BJYZCC5WYFUCSHIU4XPEVFG54A","short_pith_number":"pith:BJYZCC5W","schema_version":"1.0","canonical_sha256":"0a71910bb6c168291d14e5de4a94dde016455119af3093f0cf7ebb6387e776b7","source":{"kind":"arxiv","id":"2504.07627","version":2},"attestation_state":"computed","paper":{"title":"Robustness of Online Identification-based Policy Iteration to Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrea Iannelli, Bowen Song","submitted_at":"2025-04-10T10:24:13Z","abstract_excerpt":"This article investigates the core mechanisms of indirect data-driven control for unknown systems, focusing on the application of policy iteration (PI) within the context of the linear quadratic regulator (LQR) optimal control problem. Specifically, we consider a setting where data is collected sequentially from a linear system subject to exogenous process noise, and is then used to refine estimates of the optimal control policy. We integrate recursive least squares (RLS) for online model estimation within a certainty-equivalent framework, and employ PI to iteratively update the control policy"},"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":"2504.07627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-04-10T10:24:13Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"d60ce4d3e28ecdc5c2e2784a8e6f5fbd69f93465ac40fad5f1cbfc529310f0c6","abstract_canon_sha256":"36b7e41affbf3dae6cca6236c165ef403530246ed7c7c85c6af95d1e58d2c0b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:39.904603Z","signature_b64":"jcovAWrYI48T+b86ZT4cRBRXWZMLEckG3x9oTqnKUvYrWCr6baqwgLClMUfvB+caVmfUVIn2QC4zN7vZ2WJoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a71910bb6c168291d14e5de4a94dde016455119af3093f0cf7ebb6387e776b7","last_reissued_at":"2026-07-05T10:47:39.903966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:39.903966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness of Online Identification-based Policy Iteration to Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrea Iannelli, Bowen Song","submitted_at":"2025-04-10T10:24:13Z","abstract_excerpt":"This article investigates the core mechanisms of indirect data-driven control for unknown systems, focusing on the application of policy iteration (PI) within the context of the linear quadratic regulator (LQR) optimal control problem. Specifically, we consider a setting where data is collected sequentially from a linear system subject to exogenous process noise, and is then used to refine estimates of the optimal control policy. We integrate recursive least squares (RLS) for online model estimation within a certainty-equivalent framework, and employ PI to iteratively update the control policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07627","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/2504.07627/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":"2504.07627","created_at":"2026-07-05T10:47:39.904033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07627v2","created_at":"2026-07-05T10:47:39.904033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07627","created_at":"2026-07-05T10:47:39.904033+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJYZCC5WYFUC","created_at":"2026-07-05T10:47:39.904033+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJYZCC5WYFUCSHIU","created_at":"2026-07-05T10:47:39.904033+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJYZCC5W","created_at":"2026-07-05T10:47:39.904033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03706","citing_title":"Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A","json":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A.json","graph_json":"https://pith.science/api/pith-number/BJYZCC5WYFUCSHIU4XPEVFG54A/graph.json","events_json":"https://pith.science/api/pith-number/BJYZCC5WYFUCSHIU4XPEVFG54A/events.json","paper":"https://pith.science/paper/BJYZCC5W"},"agent_actions":{"view_html":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A","download_json":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A.json","view_paper":"https://pith.science/paper/BJYZCC5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07627&json=true","fetch_graph":"https://pith.science/api/pith-number/BJYZCC5WYFUCSHIU4XPEVFG54A/graph.json","fetch_events":"https://pith.science/api/pith-number/BJYZCC5WYFUCSHIU4XPEVFG54A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A/action/storage_attestation","attest_author":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A/action/author_attestation","sign_citation":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A/action/citation_signature","submit_replication":"https://pith.science/pith/BJYZCC5WYFUCSHIU4XPEVFG54A/action/replication_record"}},"created_at":"2026-07-05T10:47:39.904033+00:00","updated_at":"2026-07-05T10:47:39.904033+00:00"}