{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LOEMRABTU3ULBY6RQT7UX6ALDV","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":"a6642952c63b0efee178cc9a03aa61e287e54c7d206c7e1f00de145b8a69966c","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T09:32:45Z","title_canon_sha256":"c675ce77627332bf42db1c8fa86c544c79dd9de72a5ecf5d7bcc06a032170230"},"schema_version":"1.0","source":{"id":"2205.07536","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.07536","created_at":"2026-07-05T04:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2205.07536v2","created_at":"2026-07-05T04:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07536","created_at":"2026-07-05T04:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"LOEMRABTU3UL","created_at":"2026-07-05T04:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"LOEMRABTU3ULBY6R","created_at":"2026-07-05T04:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"LOEMRABT","created_at":"2026-07-05T04:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:306f3f9e9f921ac6a5e45110238fa1592a401873b95feb6c497cc8886fbf7bc8","target":"graph","created_at":"2026-07-05T04:29:33Z","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/2205.07536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Constrained reinforcement learning (CRL) has gained significant interest recently, since safety constraints satisfaction is critical for real-world problems. However, existing CRL methods constraining discounted cumulative costs generally lack rigorous definition and guarantee of safety. In contrast, in the safe control research, safety is defined as persistently satisfying certain state constraints. Such persistent safety is possible only on a subset of the state space, called feasible set, where an optimal largest feasible set exists for a given environment. Recent studies incorporate feasib","authors_text":"Dongjie Yu, Haitong Ma, Jianyu Chen, Shengbo Eben Li","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T09:32:45Z","title":"Reachability Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07536","kind":"arxiv","version":2},"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:dc1f82aaf94542f074e16b41ef4e66a7d4a9a4bb093084fd40596abf2723cf82","target":"record","created_at":"2026-07-05T04:29:33Z","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":"a6642952c63b0efee178cc9a03aa61e287e54c7d206c7e1f00de145b8a69966c","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T09:32:45Z","title_canon_sha256":"c675ce77627332bf42db1c8fa86c544c79dd9de72a5ecf5d7bcc06a032170230"},"schema_version":"1.0","source":{"id":"2205.07536","kind":"arxiv","version":2}},"canonical_sha256":"5b88c88033a6e8b0e3d184ff4bf80b1d570982256c86da0548b43fb59a3446b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b88c88033a6e8b0e3d184ff4bf80b1d570982256c86da0548b43fb59a3446b1","first_computed_at":"2026-07-05T04:29:33.704416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:33.704416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dIP2iHmJH2+N4ShHOYO9vtzG7keQxHoIbfFs6BUm4Mgi5cUoEM8C6sWbmNH6UMZsOEfyNl/nm5XdeJohNdxABw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:33.704911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.07536","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc1f82aaf94542f074e16b41ef4e66a7d4a9a4bb093084fd40596abf2723cf82","sha256:306f3f9e9f921ac6a5e45110238fa1592a401873b95feb6c497cc8886fbf7bc8"],"state_sha256":"4327df45449093dccd08d435e3e608680f0558e1e08de321d334ca433d3d046b"}