{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6HHJ6M5A5UR53GP4VVY554ZC67","short_pith_number":"pith:6HHJ6M5A","schema_version":"1.0","canonical_sha256":"f1ce9f33a0ed23dd99fcad71def322f7c512d92e1a16750c1f10af1523566ac9","source":{"kind":"arxiv","id":"2110.05415","version":2},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Gennaro Notomista, Magnus Egerstedt, Paul Glotfelter, Yousef Emam, Zsolt Kira","submitted_at":"2021-10-11T17:00:45Z","abstract_excerpt":"Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to safety-critical systems remains a challenge. An increasingly common approach to address safety involves the addition of a safety layer that projects the RL actions onto a safe set of actions. In turn, a difficulty for such frameworks is how to effectively couple RL with the safety layer to improve the learning performance. In this paper, we frame safety as "},"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":"2110.05415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-10-11T17:00:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"cb62e86e24dc0030964f526921f1741a5badd771fead93c87c76c3baa96aa113","abstract_canon_sha256":"9a91000ad527fde38e56f735e2d6a959e225d93431a9252f2e92b7ca3eab5665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:13.597898Z","signature_b64":"kry4KsL2l3uKoI+mjnqgCvpAIWkBBVN6MUNGGEgo4C+GXywmw0H62B482fNZOFHBxaVtOOKd9j06Kftf/dxfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1ce9f33a0ed23dd99fcad71def322f7c512d92e1a16750c1f10af1523566ac9","last_reissued_at":"2026-07-05T04:34:13.597436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:13.597436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Gennaro Notomista, Magnus Egerstedt, Paul Glotfelter, Yousef Emam, Zsolt Kira","submitted_at":"2021-10-11T17:00:45Z","abstract_excerpt":"Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to safety-critical systems remains a challenge. An increasingly common approach to address safety involves the addition of a safety layer that projects the RL actions onto a safe set of actions. In turn, a difficulty for such frameworks is how to effectively couple RL with the safety layer to improve the learning performance. In this paper, we frame safety as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05415","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/2110.05415/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":"2110.05415","created_at":"2026-07-05T04:34:13.597489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05415v2","created_at":"2026-07-05T04:34:13.597489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05415","created_at":"2026-07-05T04:34:13.597489+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HHJ6M5A5UR5","created_at":"2026-07-05T04:34:13.597489+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HHJ6M5A5UR53GP4","created_at":"2026-07-05T04:34:13.597489+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HHJ6M5A","created_at":"2026-07-05T04:34:13.597489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09128","citing_title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67","json":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67.json","graph_json":"https://pith.science/api/pith-number/6HHJ6M5A5UR53GP4VVY554ZC67/graph.json","events_json":"https://pith.science/api/pith-number/6HHJ6M5A5UR53GP4VVY554ZC67/events.json","paper":"https://pith.science/paper/6HHJ6M5A"},"agent_actions":{"view_html":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67","download_json":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67.json","view_paper":"https://pith.science/paper/6HHJ6M5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05415&json=true","fetch_graph":"https://pith.science/api/pith-number/6HHJ6M5A5UR53GP4VVY554ZC67/graph.json","fetch_events":"https://pith.science/api/pith-number/6HHJ6M5A5UR53GP4VVY554ZC67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67/action/storage_attestation","attest_author":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67/action/author_attestation","sign_citation":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67/action/citation_signature","submit_replication":"https://pith.science/pith/6HHJ6M5A5UR53GP4VVY554ZC67/action/replication_record"}},"created_at":"2026-07-05T04:34:13.597489+00:00","updated_at":"2026-07-05T04:34:13.597489+00:00"}