{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RHGNPTUFMZYKWU3SFUF7UWORQ3","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":"a5a432a1e4a5feb84766db2ee0e39c8a3aa5b5f4efd816a001f682610b471a1d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T21:11:29Z","title_canon_sha256":"7086802cf1e7f72c306000671598511be6d383697c1c563e8ce9005d590d54b3"},"schema_version":"1.0","source":{"id":"2302.03122","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03122","created_at":"2026-07-05T06:26:33Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03122v3","created_at":"2026-07-05T06:26:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03122","created_at":"2026-07-05T06:26:33Z"},{"alias_kind":"pith_short_12","alias_value":"RHGNPTUFMZYK","created_at":"2026-07-05T06:26:33Z"},{"alias_kind":"pith_short_16","alias_value":"RHGNPTUFMZYKWU3S","created_at":"2026-07-05T06:26:33Z"},{"alias_kind":"pith_short_8","alias_value":"RHGNPTUF","created_at":"2026-07-05T06:26:33Z"}],"graph_snapshots":[{"event_id":"sha256:4dc3753de1ff430bbdcf37bd9931a80a2a2526ebab3ed952b97428f5566afa22","target":"graph","created_at":"2026-07-05T06:26:33Z","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/2302.03122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction. State-wise constraints are one of the most common constraints in real-world applications and one of the most challenging constraints in Safe RL. Enforcing state-wise constraints is necessary and essential to many challenging tasks such as autonomous driving, robot manipulation. This paper provides a comprehensive review of existing approaches that address stat","authors_text":"Changliu Liu, Rui Chen, Tairan He, Tianhao Wei, Weiye Zhao","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T21:11:29Z","title":"State-wise Safe Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03122","kind":"arxiv","version":3},"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":"sha256:0a8223c83200583e8a9bb9ac7bf6c8b08d507d04f7d61a173dbf7f16430c4cd1","target":"record","created_at":"2026-07-05T06:26:33Z","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":"a5a432a1e4a5feb84766db2ee0e39c8a3aa5b5f4efd816a001f682610b471a1d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T21:11:29Z","title_canon_sha256":"7086802cf1e7f72c306000671598511be6d383697c1c563e8ce9005d590d54b3"},"schema_version":"1.0","source":{"id":"2302.03122","kind":"arxiv","version":3}},"canonical_sha256":"89ccd7ce856670ab53722d0bfa59d186e4b71938f788291b88df06ac08362075","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89ccd7ce856670ab53722d0bfa59d186e4b71938f788291b88df06ac08362075","first_computed_at":"2026-07-05T06:26:33.910935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:33.910935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7yj5bl4bDlZzDy60E4uXfSs+5tWkWv6IpHspBhiD5v1kzjwgwBib0Z2tcqj213TRMwEuNCzdczrv/twhKJfeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:33.911375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03122","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a8223c83200583e8a9bb9ac7bf6c8b08d507d04f7d61a173dbf7f16430c4cd1","sha256:4dc3753de1ff430bbdcf37bd9931a80a2a2526ebab3ed952b97428f5566afa22"],"state_sha256":"84a5e201bb1fde42f6c20723d7834f4c9b7008b067d0cda20c6778ede409aeda"}