{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CNSQADV7WJPG6KZJF2QOHD6PKX","short_pith_number":"pith:CNSQADV7","canonical_record":{"source":{"id":"2305.14216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"844cb1ceb056f007f8b9618a156701fae47deb78245224b64c666c367b07deca","abstract_canon_sha256":"bee2bc84bd7210e210af759cfaa591ec397f7d43b8acde68e9d2f6bf02c9dd59"},"schema_version":"1.0"},"canonical_sha256":"1365000ebfb25e6f2b292ea0e38fcf55f7950cb376ce9c68464458f140b8ffd0","source":{"kind":"arxiv","id":"2305.14216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14216","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14216v1","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14216","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"CNSQADV7WJPG","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"CNSQADV7WJPG6KZJ","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"CNSQADV7","created_at":"2026-07-05T06:13:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CNSQADV7WJPG6KZJF2QOHD6PKX","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"844cb1ceb056f007f8b9618a156701fae47deb78245224b64c666c367b07deca","abstract_canon_sha256":"bee2bc84bd7210e210af759cfaa591ec397f7d43b8acde68e9d2f6bf02c9dd59"},"schema_version":"1.0"},"canonical_sha256":"1365000ebfb25e6f2b292ea0e38fcf55f7950cb376ce9c68464458f140b8ffd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:02.131701Z","signature_b64":"BFq6PrfybX3veh3aLgzxHtqIg0MtCpa/pRKRHqG+yDOvl2RWBBJRyldjd972qIGcwa4+qvBIH7yh1tC/pVtwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1365000ebfb25e6f2b292ea0e38fcf55f7950cb376ce9c68464458f140b8ffd0","last_reissued_at":"2026-07-05T06:13:02.131232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:02.131232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14216","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnagKcMgqrN0eWzQ8SFGVnjXyU22V+zWDXhKonI/j4hof/U464G560LXGSm0YfzT99NWYwhjTnENmgRdESChDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:03:44.863036Z"},"content_sha256":"2154e2e6ed767642878b5d505036a12dd3aaa8052fb9454e1626c65efce53391","schema_version":"1.0","event_id":"sha256:2154e2e6ed767642878b5d505036a12dd3aaa8052fb9454e1626c65efce53391"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CNSQADV7WJPG6KZJF2QOHD6PKX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Proximal Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengbin Xuan, Faliang Yin, Feng Zhang, Hak-Keung Lam","submitted_at":"2023-05-23T16:33:55Z","abstract_excerpt":"The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, with the introduction of constraint satisfaction, the current CRL methods necessitate the utilization of second-order optimization or primal-dual frameworks with additional Lagrangian multipliers, resulting in increased complexity and inefficiency during implementation. To address these issues, we propose a novel first-order feasible method named Constrained Proximal Policy Opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14216","kind":"arxiv","version":1},"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/2305.14216/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":"2026-07-05T06:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTKGOFPYfYwXUNRwe9D2wlUaW8/FrEo9SrVGmXeKXWtHs5zjGduu2SSVlQZVu7f1lW6ve+HoMnvGQSy34j3oCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:03:44.863431Z"},"content_sha256":"aafec3389b3df97681e04f1d4b6ae103505057526d958c567e64826c2d666725","schema_version":"1.0","event_id":"sha256:aafec3389b3df97681e04f1d4b6ae103505057526d958c567e64826c2d666725"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNSQADV7WJPG6KZJF2QOHD6PKX/bundle.json","state_url":"https://pith.science/pith/CNSQADV7WJPG6KZJF2QOHD6PKX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNSQADV7WJPG6KZJF2QOHD6PKX/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":"2026-08-19T02:03:44Z","links":{"resolver":"https://pith.science/pith/CNSQADV7WJPG6KZJF2QOHD6PKX","bundle":"https://pith.science/pith/CNSQADV7WJPG6KZJF2QOHD6PKX/bundle.json","state":"https://pith.science/pith/CNSQADV7WJPG6KZJF2QOHD6PKX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNSQADV7WJPG6KZJF2QOHD6PKX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CNSQADV7WJPG6KZJF2QOHD6PKX","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":"bee2bc84bd7210e210af759cfaa591ec397f7d43b8acde68e9d2f6bf02c9dd59","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:33:55Z","title_canon_sha256":"844cb1ceb056f007f8b9618a156701fae47deb78245224b64c666c367b07deca"},"schema_version":"1.0","source":{"id":"2305.14216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14216","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14216v1","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14216","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"CNSQADV7WJPG","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"CNSQADV7WJPG6KZJ","created_at":"2026-07-05T06:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"CNSQADV7","created_at":"2026-07-05T06:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:aafec3389b3df97681e04f1d4b6ae103505057526d958c567e64826c2d666725","target":"graph","created_at":"2026-07-05T06:13:02Z","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/2305.14216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, with the introduction of constraint satisfaction, the current CRL methods necessitate the utilization of second-order optimization or primal-dual frameworks with additional Lagrangian multipliers, resulting in increased complexity and inefficiency during implementation. To address these issues, we propose a novel first-order feasible method named Constrained Proximal Policy Opti","authors_text":"Chengbin Xuan, Faliang Yin, Feng Zhang, Hak-Keung Lam","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:33:55Z","title":"Constrained Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14216","kind":"arxiv","version":1},"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":"sha256:2154e2e6ed767642878b5d505036a12dd3aaa8052fb9454e1626c65efce53391","target":"record","created_at":"2026-07-05T06:13:02Z","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":"bee2bc84bd7210e210af759cfaa591ec397f7d43b8acde68e9d2f6bf02c9dd59","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T16:33:55Z","title_canon_sha256":"844cb1ceb056f007f8b9618a156701fae47deb78245224b64c666c367b07deca"},"schema_version":"1.0","source":{"id":"2305.14216","kind":"arxiv","version":1}},"canonical_sha256":"1365000ebfb25e6f2b292ea0e38fcf55f7950cb376ce9c68464458f140b8ffd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1365000ebfb25e6f2b292ea0e38fcf55f7950cb376ce9c68464458f140b8ffd0","first_computed_at":"2026-07-05T06:13:02.131232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:02.131232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BFq6PrfybX3veh3aLgzxHtqIg0MtCpa/pRKRHqG+yDOvl2RWBBJRyldjd972qIGcwa4+qvBIH7yh1tC/pVtwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:02.131701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2154e2e6ed767642878b5d505036a12dd3aaa8052fb9454e1626c65efce53391","sha256:aafec3389b3df97681e04f1d4b6ae103505057526d958c567e64826c2d666725"],"state_sha256":"2ce63abbaee54d6ba41afd17f0e097d761a30211661a38fdfabd9b3956d591e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QuU1umzkjtw9FnnB5aCygRDG6OV9is7NAc2NGFaIzsVnCgppQTYoK/5a18LQenmTg7AAXVtqKg7AuB+McxCTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:03:44.866642Z","bundle_sha256":"25021c61bfc2c83b48d4d90d0eae73642ade1e3efe8b2cbcd8ca136af11b5d16"}}