{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NAFCPRINCE7P6ZAAFSGNMPQGZS","short_pith_number":"pith:NAFCPRIN","schema_version":"1.0","canonical_sha256":"680a27c50d113eff64002c8cd63e06cca3c45038979cb3a4df6e690402398d8f","source":{"kind":"arxiv","id":"2206.07915","version":2},"attestation_state":"computed","paper":{"title":"Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Dongkun Han, Hejun Huang, Zhenglong Li","submitted_at":"2022-06-16T04:38:50Z","abstract_excerpt":"Safety guarantee is essential in many engineering implementations. Reinforcement learning provides a useful way to strengthen safety. However, reinforcement learning algorithms cannot completely guarantee safety over realistic operations. To address this issue, this work adopts control barrier functions over reinforcement learning, and proposes a compensated algorithm to completely maintain safety. Specifically, a sum-of-squares programming has been exploited to search for the optimal controller, and tune the learning hyperparameters simultaneously. Thus, the control actions are pledged to be "},"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":"2206.07915","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2022-06-16T04:38:50Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"a10916c918f1f5eba4b049361ea02823aa56c2c5e861d8251b3102dc275a225d","abstract_canon_sha256":"b2a5c007683b3e83c43b9efebc07669b9f821419a19cd14fb607b2914ce63910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:10.496038Z","signature_b64":"1GxHdEWLyy3fhA8oXsc+JL/AMO+RZTUZvlqWFCHOVJK8pNsyhXkFLB3ESYvK3URE3P6glsCmvLpSMuhhNzjFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"680a27c50d113eff64002c8cd63e06cca3c45038979cb3a4df6e690402398d8f","last_reissued_at":"2026-07-05T04:36:10.495532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:10.495532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Dongkun Han, Hejun Huang, Zhenglong Li","submitted_at":"2022-06-16T04:38:50Z","abstract_excerpt":"Safety guarantee is essential in many engineering implementations. Reinforcement learning provides a useful way to strengthen safety. However, reinforcement learning algorithms cannot completely guarantee safety over realistic operations. To address this issue, this work adopts control barrier functions over reinforcement learning, and proposes a compensated algorithm to completely maintain safety. Specifically, a sum-of-squares programming has been exploited to search for the optimal controller, and tune the learning hyperparameters simultaneously. Thus, the control actions are pledged to be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07915","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/2206.07915/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":"2206.07915","created_at":"2026-07-05T04:36:10.495595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07915v2","created_at":"2026-07-05T04:36:10.495595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07915","created_at":"2026-07-05T04:36:10.495595+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAFCPRINCE7P","created_at":"2026-07-05T04:36:10.495595+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAFCPRINCE7P6ZAA","created_at":"2026-07-05T04:36:10.495595+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAFCPRIN","created_at":"2026-07-05T04:36:10.495595+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/NAFCPRINCE7P6ZAAFSGNMPQGZS","json":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS.json","graph_json":"https://pith.science/api/pith-number/NAFCPRINCE7P6ZAAFSGNMPQGZS/graph.json","events_json":"https://pith.science/api/pith-number/NAFCPRINCE7P6ZAAFSGNMPQGZS/events.json","paper":"https://pith.science/paper/NAFCPRIN"},"agent_actions":{"view_html":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS","download_json":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS.json","view_paper":"https://pith.science/paper/NAFCPRIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07915&json=true","fetch_graph":"https://pith.science/api/pith-number/NAFCPRINCE7P6ZAAFSGNMPQGZS/graph.json","fetch_events":"https://pith.science/api/pith-number/NAFCPRINCE7P6ZAAFSGNMPQGZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS/action/storage_attestation","attest_author":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS/action/author_attestation","sign_citation":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS/action/citation_signature","submit_replication":"https://pith.science/pith/NAFCPRINCE7P6ZAAFSGNMPQGZS/action/replication_record"}},"created_at":"2026-07-05T04:36:10.495595+00:00","updated_at":"2026-07-05T04:36:10.495595+00:00"}