{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZLTM6X5YD36NBISNMILQMZ33NG","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":"94b0cfae41c6527c37d27968db44bab9bd3f682135c76e9db8fa20ba2a18cef2","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T22:28:17Z","title_canon_sha256":"c30534c7c0793e6725b27c57739430985be7f4651b661f00d2805ded1792e82b"},"schema_version":"1.0","source":{"id":"2306.12594","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12594","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12594v3","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12594","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZLTM6X5YD36N","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZLTM6X5YD36NBISN","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZLTM6X5Y","created_at":"2026-07-05T08:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:5a188c04de9c0a52365c011c63113f8f147ab599ee01c9c3128d0078d2be7e9a","target":"graph","created_at":"2026-07-05T08:32:59Z","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/2306.12594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing state-wise constraints is essential for many challenging tasks such as autonomous driving and robot manipulation. However, existing safe RL algorithms under the framework of Constrained Markov Decision Process (CMDP) do not consider state-wise constraints. To address this gap, we propose State-wise Constrained Policy Optimization (SCPO), the first general-purpose po","authors_text":"Changliu Liu, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T22:28:17Z","title":"State-wise Constrained Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12594","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":"sha256:7ab6ce52c926e0db873eb8674a0d3fc5e7865feb8507f13944a12b194ac3121d","target":"record","created_at":"2026-07-05T08:32:59Z","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":"94b0cfae41c6527c37d27968db44bab9bd3f682135c76e9db8fa20ba2a18cef2","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T22:28:17Z","title_canon_sha256":"c30534c7c0793e6725b27c57739430985be7f4651b661f00d2805ded1792e82b"},"schema_version":"1.0","source":{"id":"2306.12594","kind":"arxiv","version":3}},"canonical_sha256":"cae6cf5fb81efcd0a24d621706677b69b0b1a52ca9a9dfb403ca087c0c1812c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cae6cf5fb81efcd0a24d621706677b69b0b1a52ca9a9dfb403ca087c0c1812c2","first_computed_at":"2026-07-05T08:32:59.334661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:59.334661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Xbq0c6ZYSrEM8IHHOUEt7oWq4WE3rddLuS0vW4P2zwUR+Rls4rYKfn2t9bCjRvG3w3oLp2ANHkG5DaIaXrrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:59.335134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.12594","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ab6ce52c926e0db873eb8674a0d3fc5e7865feb8507f13944a12b194ac3121d","sha256:5a188c04de9c0a52365c011c63113f8f147ab599ee01c9c3128d0078d2be7e9a"],"state_sha256":"3272498037e11e406a088f39246c0d7bb6dc50360e01071f41fde1c57fe473d6"}