{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y24LWBM3AH2RKZJ7GQTF2YFIZI","short_pith_number":"pith:Y24LWBM3","schema_version":"1.0","canonical_sha256":"c6b8bb059b01f515653f34265d60a8ca06a01626ee3b1be5bd7585267557ec53","source":{"kind":"arxiv","id":"2204.01409","version":1},"attestation_state":"computed","paper":{"title":"Safe Controller for Output Feedback Linear Systems using Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Moad Abudia, Rushikesh Kamalapurkar, Scott A Nivison, S M Nahid Mahmud, Zachary I. Bell","submitted_at":"2022-04-04T11:57:40Z","abstract_excerpt":"The objective of this research is to enable safety-critical systems to simultaneously learn and execute optimal control policies in a safe manner to achieve complex autonomy. Learning optimal policies via trial and error, i.e., traditional reinforcement learning, is difficult to implement in safety-critical systems, particularly when task restarts are unavailable. Safe model-based reinforcement learning techniques based on a barrier transformation have recently been developed to address this problem. However, these methods rely on full state feedback, limiting their usability in a real-world e"},"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":"2204.01409","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-04-04T11:57:40Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"7014997c8b10e089879e126d265421c6fbc495a85125fd409c5a0e424a5eb85e","abstract_canon_sha256":"f4f580f4e5f53f04b9cfd944a5d8a08b1393ced7af66702ea53db7b52e1e6822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:18.572879Z","signature_b64":"RTLzPxQXMW3cbLiDu4yUbfP9tNNOl6Vz40ON82xRhBhWWT5+wVbLNOo1MHw7oWcRMHeVw1HYTCj7B0gH8wkGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6b8bb059b01f515653f34265d60a8ca06a01626ee3b1be5bd7585267557ec53","last_reissued_at":"2026-07-05T04:11:18.572340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:18.572340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Controller for Output Feedback Linear Systems using Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Moad Abudia, Rushikesh Kamalapurkar, Scott A Nivison, S M Nahid Mahmud, Zachary I. Bell","submitted_at":"2022-04-04T11:57:40Z","abstract_excerpt":"The objective of this research is to enable safety-critical systems to simultaneously learn and execute optimal control policies in a safe manner to achieve complex autonomy. Learning optimal policies via trial and error, i.e., traditional reinforcement learning, is difficult to implement in safety-critical systems, particularly when task restarts are unavailable. Safe model-based reinforcement learning techniques based on a barrier transformation have recently been developed to address this problem. However, these methods rely on full state feedback, limiting their usability in a real-world e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01409","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/2204.01409/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":"2204.01409","created_at":"2026-07-05T04:11:18.572412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.01409v1","created_at":"2026-07-05T04:11:18.572412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01409","created_at":"2026-07-05T04:11:18.572412+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y24LWBM3AH2R","created_at":"2026-07-05T04:11:18.572412+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y24LWBM3AH2RKZJ7","created_at":"2026-07-05T04:11:18.572412+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y24LWBM3","created_at":"2026-07-05T04:11:18.572412+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/Y24LWBM3AH2RKZJ7GQTF2YFIZI","json":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI.json","graph_json":"https://pith.science/api/pith-number/Y24LWBM3AH2RKZJ7GQTF2YFIZI/graph.json","events_json":"https://pith.science/api/pith-number/Y24LWBM3AH2RKZJ7GQTF2YFIZI/events.json","paper":"https://pith.science/paper/Y24LWBM3"},"agent_actions":{"view_html":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI","download_json":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI.json","view_paper":"https://pith.science/paper/Y24LWBM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.01409&json=true","fetch_graph":"https://pith.science/api/pith-number/Y24LWBM3AH2RKZJ7GQTF2YFIZI/graph.json","fetch_events":"https://pith.science/api/pith-number/Y24LWBM3AH2RKZJ7GQTF2YFIZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI/action/storage_attestation","attest_author":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI/action/author_attestation","sign_citation":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI/action/citation_signature","submit_replication":"https://pith.science/pith/Y24LWBM3AH2RKZJ7GQTF2YFIZI/action/replication_record"}},"created_at":"2026-07-05T04:11:18.572412+00:00","updated_at":"2026-07-05T04:11:18.572412+00:00"}