{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P2CVPWCDMUSCHIHGAHZR5MKOTT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9cb058e1070115cc9d696cd463eeeee4352cd2f3a4479d51331c3fa4eced8dc1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T21:41:31Z","title_canon_sha256":"afb7757cec42d6717a886d8ec7ac24f2a24c9e4f82eacedc662b09cb1009f142"},"schema_version":"1.0","source":{"id":"2306.04026","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04026","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04026v4","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04026","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"P2CVPWCDMUSC","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"P2CVPWCDMUSCHIHG","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"P2CVPWCD","created_at":"2026-07-05T07:20:08Z"}],"graph_snapshots":[{"event_id":"sha256:19ee6e4c9d28d3618a1b04a7d66823ff3db03e8e05f0d51099500e62412cce43","target":"graph","created_at":"2026-07-05T07:20:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.04026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Guaranteeing safe behaviour of reinforcement learning (RL) policies poses significant challenges for safety-critical applications, despite RL's generality and scalability. To address this, we propose a new approach to apply verification methods from control theory to learned value functions. By analyzing task structures for safety preservation, we formalize original theorems that establish links between value functions and control barrier functions. Further, we propose novel metrics for verifying value functions in safe control tasks and practical implementation details to improve learning. Ou","authors_text":"Daniel C.H. Tan, Dimitrios Kanoulas, Fernando Acero, Robert McCarthy, Zhibin Li","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T21:41:31Z","title":"Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04026","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ec5a96d34e407f92cfe8128f6183d80adc37895e629b10822d26a6751686aa6a","target":"record","created_at":"2026-07-05T07:20:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9cb058e1070115cc9d696cd463eeeee4352cd2f3a4479d51331c3fa4eced8dc1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T21:41:31Z","title_canon_sha256":"afb7757cec42d6717a886d8ec7ac24f2a24c9e4f82eacedc662b09cb1009f142"},"schema_version":"1.0","source":{"id":"2306.04026","kind":"arxiv","version":4}},"canonical_sha256":"7e8557d843652423a0e601f31eb14e9cc802d71cdd6e586e5f2f762a93c07432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e8557d843652423a0e601f31eb14e9cc802d71cdd6e586e5f2f762a93c07432","first_computed_at":"2026-07-05T07:20:08.850558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:08.850558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e97NyNHyz+SCFJzriRUjs8rAEbOCjMjvyT3wV/YFNQzOHtJkksDcxDaurT0h+CzrepkQ2i/RjvEhhXJneA4bBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:08.850955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04026","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec5a96d34e407f92cfe8128f6183d80adc37895e629b10822d26a6751686aa6a","sha256:19ee6e4c9d28d3618a1b04a7d66823ff3db03e8e05f0d51099500e62412cce43"],"state_sha256":"881d1960f98696d6dc91e84b78f5736aaa1e044e0dd00dcac7f6943ed4cba4d4"}