{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RHGNPTUFMZYKWU3SFUF7UWORQ3","short_pith_number":"pith:RHGNPTUF","schema_version":"1.0","canonical_sha256":"89ccd7ce856670ab53722d0bfa59d186e4b71938f788291b88df06ac08362075","source":{"kind":"arxiv","id":"2302.03122","version":3},"attestation_state":"computed","paper":{"title":"State-wise Safe Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Rui Chen, Tairan He, Tianhao Wei, Weiye Zhao","submitted_at":"2023-02-06T21:11:29Z","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"},"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":"2302.03122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T21:11:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"7086802cf1e7f72c306000671598511be6d383697c1c563e8ce9005d590d54b3","abstract_canon_sha256":"a5a432a1e4a5feb84766db2ee0e39c8a3aa5b5f4efd816a001f682610b471a1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:33.911375Z","signature_b64":"7yj5bl4bDlZzDy60E4uXfSs+5tWkWv6IpHspBhiD5v1kzjwgwBib0Z2tcqj213TRMwEuNCzdczrv/twhKJfeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ccd7ce856670ab53722d0bfa59d186e4b71938f788291b88df06ac08362075","last_reissued_at":"2026-07-05T06:26:33.910935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:33.910935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-wise Safe Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Rui Chen, Tairan He, Tianhao Wei, Weiye Zhao","submitted_at":"2023-02-06T21:11:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03122","kind":"arxiv","version":3},"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/2302.03122/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":"2302.03122","created_at":"2026-07-05T06:26:33.910997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03122v3","created_at":"2026-07-05T06:26:33.910997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03122","created_at":"2026-07-05T06:26:33.910997+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHGNPTUFMZYK","created_at":"2026-07-05T06:26:33.910997+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHGNPTUFMZYKWU3S","created_at":"2026-07-05T06:26:33.910997+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHGNPTUF","created_at":"2026-07-05T06:26:33.910997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28764","citing_title":"Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16033","citing_title":"Safe Deep Reinforcement Learning for Building Heating Control and Demand-side Flexibility","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3","json":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3.json","graph_json":"https://pith.science/api/pith-number/RHGNPTUFMZYKWU3SFUF7UWORQ3/graph.json","events_json":"https://pith.science/api/pith-number/RHGNPTUFMZYKWU3SFUF7UWORQ3/events.json","paper":"https://pith.science/paper/RHGNPTUF"},"agent_actions":{"view_html":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3","download_json":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3.json","view_paper":"https://pith.science/paper/RHGNPTUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03122&json=true","fetch_graph":"https://pith.science/api/pith-number/RHGNPTUFMZYKWU3SFUF7UWORQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/RHGNPTUFMZYKWU3SFUF7UWORQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3/action/storage_attestation","attest_author":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3/action/author_attestation","sign_citation":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3/action/citation_signature","submit_replication":"https://pith.science/pith/RHGNPTUFMZYKWU3SFUF7UWORQ3/action/replication_record"}},"created_at":"2026-07-05T06:26:33.910997+00:00","updated_at":"2026-07-05T06:26:33.910997+00:00"}