{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZLTM6X5YD36NBISNMILQMZ33NG","short_pith_number":"pith:ZLTM6X5Y","canonical_record":{"source":{"id":"2306.12594","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T22:28:17Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c30534c7c0793e6725b27c57739430985be7f4651b661f00d2805ded1792e82b","abstract_canon_sha256":"94b0cfae41c6527c37d27968db44bab9bd3f682135c76e9db8fa20ba2a18cef2"},"schema_version":"1.0"},"canonical_sha256":"cae6cf5fb81efcd0a24d621706677b69b0b1a52ca9a9dfb403ca087c0c1812c2","source":{"kind":"arxiv","id":"2306.12594","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZLTM6X5YD36NBISNMILQMZ33NG","target":"record","payload":{"canonical_record":{"source":{"id":"2306.12594","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T22:28:17Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c30534c7c0793e6725b27c57739430985be7f4651b661f00d2805ded1792e82b","abstract_canon_sha256":"94b0cfae41c6527c37d27968db44bab9bd3f682135c76e9db8fa20ba2a18cef2"},"schema_version":"1.0"},"canonical_sha256":"cae6cf5fb81efcd0a24d621706677b69b0b1a52ca9a9dfb403ca087c0c1812c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:59.335134Z","signature_b64":"/Xbq0c6ZYSrEM8IHHOUEt7oWq4WE3rddLuS0vW4P2zwUR+Rls4rYKfn2t9bCjRvG3w3oLp2ANHkG5DaIaXrrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cae6cf5fb81efcd0a24d621706677b69b0b1a52ca9a9dfb403ca087c0c1812c2","last_reissued_at":"2026-07-05T08:32:59.334661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:59.334661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.12594","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1dW/OGoadWVHa86d/WyRNCGgw/69Kj9FlGKF1QU9gttsxhFR+cBv3osHDmv/36F1FZuQnfHsFERO5jSBv/+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:59:25.287771Z"},"content_sha256":"7ab6ce52c926e0db873eb8674a0d3fc5e7865feb8507f13944a12b194ac3121d","schema_version":"1.0","event_id":"sha256:7ab6ce52c926e0db873eb8674a0d3fc5e7865feb8507f13944a12b194ac3121d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZLTM6X5YD36NBISNMILQMZ33NG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-wise Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun","submitted_at":"2023-06-21T22:28:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12594","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/2306.12594/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tyjVVCWBozqg8Au9aEJEJChMMyLR41oqvBc7tTWAO50lko6Qsd/Np2zYH6SNQBWPrCgx1he9H3v5JAX16gvHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:59:25.288720Z"},"content_sha256":"5a188c04de9c0a52365c011c63113f8f147ab599ee01c9c3128d0078d2be7e9a","schema_version":"1.0","event_id":"sha256:5a188c04de9c0a52365c011c63113f8f147ab599ee01c9c3128d0078d2be7e9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLTM6X5YD36NBISNMILQMZ33NG/bundle.json","state_url":"https://pith.science/pith/ZLTM6X5YD36NBISNMILQMZ33NG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLTM6X5YD36NBISNMILQMZ33NG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T17:59:25Z","links":{"resolver":"https://pith.science/pith/ZLTM6X5YD36NBISNMILQMZ33NG","bundle":"https://pith.science/pith/ZLTM6X5YD36NBISNMILQMZ33NG/bundle.json","state":"https://pith.science/pith/ZLTM6X5YD36NBISNMILQMZ33NG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLTM6X5YD36NBISNMILQMZ33NG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yAyBr4/BmdX05xdnnaVNGxUgZBHa9xGqDfwUdcMsCmdE4TTY1sADlf4O9fFVQWL2ETMggCZCjin3/DQXXoACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:59:25.294060Z","bundle_sha256":"14deb2a8d3157d1a7ac6ee30f16828af910fd4b608b68d47a541af1559c31d45"}}