{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:X5HZOBMU2FTGIX4CGMOBNBMMHY","short_pith_number":"pith:X5HZOBMU","canonical_record":{"source":{"id":"2202.07565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T16:49:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0e62b809c4885835d85629f54a5df4368888cc7c4980b8b262a32e05c87ea98","abstract_canon_sha256":"baeaa71367ee84484a9a3c5d61388af98fbf98579d5f073715227a0372bdfd43"},"schema_version":"1.0"},"canonical_sha256":"bf4f970594d166645f82331c16858c3e1bd45f3f9899ee377688077f1004dae2","source":{"kind":"arxiv","id":"2202.07565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07565","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07565v1","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07565","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"X5HZOBMU2FTG","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"X5HZOBMU2FTGIX4C","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"X5HZOBMU","created_at":"2026-07-05T03:57:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:X5HZOBMU2FTGIX4CGMOBNBMMHY","target":"record","payload":{"canonical_record":{"source":{"id":"2202.07565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T16:49:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0e62b809c4885835d85629f54a5df4368888cc7c4980b8b262a32e05c87ea98","abstract_canon_sha256":"baeaa71367ee84484a9a3c5d61388af98fbf98579d5f073715227a0372bdfd43"},"schema_version":"1.0"},"canonical_sha256":"bf4f970594d166645f82331c16858c3e1bd45f3f9899ee377688077f1004dae2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:01.385121Z","signature_b64":"VlwTQYLUBuPukojUCAJ4JNIe/4UvadLJZm2HJmH/iQZY+PtOLmrCSGZMmEAhuOT2eX5RMJXjfk7vzF8P8eV3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4f970594d166645f82331c16858c3e1bd45f3f9899ee377688077f1004dae2","last_reissued_at":"2026-07-05T03:57:01.384669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:01.384669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.07565","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":"2026-07-05T03:57:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yOTwPUXORrpy5nzaI2DiZnvMT+AOHPt8GuEQn51SwF02u/7hSE2X+n4uu2SLZcdB4wxeuTIpX3oBadxQ6o9cBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:18:25.755410Z"},"content_sha256":"337c976576f5c8d0c65aff81ab081f6ccb11679c81d029838e6e8ea9f8fc77b3","schema_version":"1.0","event_id":"sha256:337c976576f5c8d0c65aff81ab081f6ccb11679c81d029838e6e8ea9f8fc77b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:X5HZOBMU2FTGIX4CGMOBNBMMHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gang Pan, Jiaming Ji, Juntao Dai, Long Yang, Pengfei Li, Yu Zhang","submitted_at":"2022-02-15T16:49:28Z","abstract_excerpt":"Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a Conservative Update Policy algorithm with a theoretical safety guarantee. We derive the CUP based on the new proposed performance bounds and surrogate functions. Although using bounds as surrogate functions to design safe RL algorithms have appeared in some existing works, we develop them at least three aspects: (i) We provide a rigorous theoretical analysis to extend the surrogate functions to generalized advantage e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07565","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/2202.07565/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":"2026-07-05T03:57:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKrN5jfjfhazOZMIQzjbVqRBuV97LSHdTiZb6UjzKWdqMhq+3yCMs8xBeUBtdi/i++2iKCcEjVN2CX1DLPLEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:18:25.756336Z"},"content_sha256":"93d7033093b26c7ed980a9eaf77b598269769f654593b3e5f483f6843beecdf9","schema_version":"1.0","event_id":"sha256:93d7033093b26c7ed980a9eaf77b598269769f654593b3e5f483f6843beecdf9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY/bundle.json","state_url":"https://pith.science/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY/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":"2026-08-07T12:18:25Z","links":{"resolver":"https://pith.science/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY","bundle":"https://pith.science/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY/bundle.json","state":"https://pith.science/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5HZOBMU2FTGIX4CGMOBNBMMHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X5HZOBMU2FTGIX4CGMOBNBMMHY","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":"baeaa71367ee84484a9a3c5d61388af98fbf98579d5f073715227a0372bdfd43","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T16:49:28Z","title_canon_sha256":"c0e62b809c4885835d85629f54a5df4368888cc7c4980b8b262a32e05c87ea98"},"schema_version":"1.0","source":{"id":"2202.07565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07565","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07565v1","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07565","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"X5HZOBMU2FTG","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"X5HZOBMU2FTGIX4C","created_at":"2026-07-05T03:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"X5HZOBMU","created_at":"2026-07-05T03:57:01Z"}],"graph_snapshots":[{"event_id":"sha256:93d7033093b26c7ed980a9eaf77b598269769f654593b3e5f483f6843beecdf9","target":"graph","created_at":"2026-07-05T03:57:01Z","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/2202.07565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a Conservative Update Policy algorithm with a theoretical safety guarantee. We derive the CUP based on the new proposed performance bounds and surrogate functions. Although using bounds as surrogate functions to design safe RL algorithms have appeared in some existing works, we develop them at least three aspects: (i) We provide a rigorous theoretical analysis to extend the surrogate functions to generalized advantage e","authors_text":"Gang Pan, Jiaming Ji, Juntao Dai, Long Yang, Pengfei Li, Yu Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T16:49:28Z","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07565","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":"sha256:337c976576f5c8d0c65aff81ab081f6ccb11679c81d029838e6e8ea9f8fc77b3","target":"record","created_at":"2026-07-05T03:57:01Z","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":"baeaa71367ee84484a9a3c5d61388af98fbf98579d5f073715227a0372bdfd43","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T16:49:28Z","title_canon_sha256":"c0e62b809c4885835d85629f54a5df4368888cc7c4980b8b262a32e05c87ea98"},"schema_version":"1.0","source":{"id":"2202.07565","kind":"arxiv","version":1}},"canonical_sha256":"bf4f970594d166645f82331c16858c3e1bd45f3f9899ee377688077f1004dae2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf4f970594d166645f82331c16858c3e1bd45f3f9899ee377688077f1004dae2","first_computed_at":"2026-07-05T03:57:01.384669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:01.384669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VlwTQYLUBuPukojUCAJ4JNIe/4UvadLJZm2HJmH/iQZY+PtOLmrCSGZMmEAhuOT2eX5RMJXjfk7vzF8P8eV3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:01.385121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.07565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:337c976576f5c8d0c65aff81ab081f6ccb11679c81d029838e6e8ea9f8fc77b3","sha256:93d7033093b26c7ed980a9eaf77b598269769f654593b3e5f483f6843beecdf9"],"state_sha256":"07ad3b003a75251e98505caad0bf60f1f7998de6f07965703b89bae304e8ba70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFBieDEmF1rEN5hTr7Xtp6fMyXicJAZbxmw3yAONDUXV7NGkVChqSjOFNFmDaETaqjRII+dytVUzEPw7xpk0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:18:25.776428Z","bundle_sha256":"1837b3bc8e03951bb30c3e6d9423a9376327ad5727645ae06f848f3a089aa3eb"}}