{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TVHBCYZJ3VDRLPJQI4KXGUAT75","short_pith_number":"pith:TVHBCYZJ","canonical_record":{"source":{"id":"2206.04436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T11:57:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56eb59dd6680d3e63888681c71b5f108be3aba591107f520f6c82a6938bb6dc3","abstract_canon_sha256":"4f883285333072286e1db1f2b7742f8969d8b4b255bfbcd62c3f75893ef7742d"},"schema_version":"1.0"},"canonical_sha256":"9d4e116329dd4715bd304715735013ff57aba1651a05918fdfa1c22bceec0229","source":{"kind":"arxiv","id":"2206.04436","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04436","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04436v2","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04436","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"TVHBCYZJ3VDR","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"TVHBCYZJ3VDRLPJQ","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"TVHBCYZJ","created_at":"2026-07-05T11:04:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TVHBCYZJ3VDRLPJQI4KXGUAT75","target":"record","payload":{"canonical_record":{"source":{"id":"2206.04436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T11:57:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56eb59dd6680d3e63888681c71b5f108be3aba591107f520f6c82a6938bb6dc3","abstract_canon_sha256":"4f883285333072286e1db1f2b7742f8969d8b4b255bfbcd62c3f75893ef7742d"},"schema_version":"1.0"},"canonical_sha256":"9d4e116329dd4715bd304715735013ff57aba1651a05918fdfa1c22bceec0229","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:32.996279Z","signature_b64":"uQaCP8HiEn39r3U+uLiKFZAABBy/a+6CmyEL2VDvNbKE7FFCVfVz91/rX0hhw8VJj0o6crqkUhK2mWL0uJwWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d4e116329dd4715bd304715735013ff57aba1651a05918fdfa1c22bceec0229","last_reissued_at":"2026-07-05T11:04:32.995807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:32.995807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.04436","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRraWeo1yDxsXDvk/W/K5NtZwcO093fgH54azsOPzgJUjs0FJX4QPFtxtl3vKLSNksMJ140NNMk830mZ5fpJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:28:26.515991Z"},"content_sha256":"9a72accbbab020e99a72e90982ff52c0fb7720bb78d38ae93c23287c7715b19c","schema_version":"1.0","event_id":"sha256:9a72accbbab020e99a72e90982ff52c0fb7720bb78d38ae93c23287c7715b19c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TVHBCYZJ3VDRLPJQI4KXGUAT75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengyang Ying, Dong Yan, Hang Su, Jun Zhu, Ning Chen, Xinning Zhou","submitted_at":"2022-06-09T11:57:54Z","abstract_excerpt":"Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observation. Most of the existing methods for safe reinforcement learning can only handle transition disturbance or observation disturbance since these two kinds of disturbance affect different parts of the agent; besides, the popular worst-case return may lead to overly pessimistic policies. To address these issues, we first theoretically prove that the performance degradation under transition disturbance and observation dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04436","kind":"arxiv","version":2},"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/2206.04436/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":"2026-07-05T11:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHOFXqSAZPcyVxyLlBNCmETzPJPm6gkXljzsqwNjgSWv9Y0g2FnDDQ9baZt3AegUqgOhzcbykpr+237wznylBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:28:26.516713Z"},"content_sha256":"4f622e89cbb4687961ed4b5a992fecbd96d868866c703f8781d3ea1032de7930","schema_version":"1.0","event_id":"sha256:4f622e89cbb4687961ed4b5a992fecbd96d868866c703f8781d3ea1032de7930"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75/bundle.json","state_url":"https://pith.science/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75/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":"2026-08-09T12:28:26Z","links":{"resolver":"https://pith.science/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75","bundle":"https://pith.science/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75/bundle.json","state":"https://pith.science/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVHBCYZJ3VDRLPJQI4KXGUAT75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TVHBCYZJ3VDRLPJQI4KXGUAT75","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":"4f883285333072286e1db1f2b7742f8969d8b4b255bfbcd62c3f75893ef7742d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T11:57:54Z","title_canon_sha256":"56eb59dd6680d3e63888681c71b5f108be3aba591107f520f6c82a6938bb6dc3"},"schema_version":"1.0","source":{"id":"2206.04436","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04436","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04436v2","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04436","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"TVHBCYZJ3VDR","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"TVHBCYZJ3VDRLPJQ","created_at":"2026-07-05T11:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"TVHBCYZJ","created_at":"2026-07-05T11:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:4f622e89cbb4687961ed4b5a992fecbd96d868866c703f8781d3ea1032de7930","target":"graph","created_at":"2026-07-05T11:04:32Z","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/2206.04436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observation. Most of the existing methods for safe reinforcement learning can only handle transition disturbance or observation disturbance since these two kinds of disturbance affect different parts of the agent; besides, the popular worst-case return may lead to overly pessimistic policies. To address these issues, we first theoretically prove that the performance degradation under transition disturbance and observation dist","authors_text":"Chengyang Ying, Dong Yan, Hang Su, Jun Zhu, Ning Chen, Xinning Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T11:57:54Z","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04436","kind":"arxiv","version":2},"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":"sha256:9a72accbbab020e99a72e90982ff52c0fb7720bb78d38ae93c23287c7715b19c","target":"record","created_at":"2026-07-05T11:04:32Z","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":"4f883285333072286e1db1f2b7742f8969d8b4b255bfbcd62c3f75893ef7742d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T11:57:54Z","title_canon_sha256":"56eb59dd6680d3e63888681c71b5f108be3aba591107f520f6c82a6938bb6dc3"},"schema_version":"1.0","source":{"id":"2206.04436","kind":"arxiv","version":2}},"canonical_sha256":"9d4e116329dd4715bd304715735013ff57aba1651a05918fdfa1c22bceec0229","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d4e116329dd4715bd304715735013ff57aba1651a05918fdfa1c22bceec0229","first_computed_at":"2026-07-05T11:04:32.995807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:32.995807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQaCP8HiEn39r3U+uLiKFZAABBy/a+6CmyEL2VDvNbKE7FFCVfVz91/rX0hhw8VJj0o6crqkUhK2mWL0uJwWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:32.996279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04436","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a72accbbab020e99a72e90982ff52c0fb7720bb78d38ae93c23287c7715b19c","sha256:4f622e89cbb4687961ed4b5a992fecbd96d868866c703f8781d3ea1032de7930"],"state_sha256":"d52db31520709228fea16afda17f3aa8010c19d2e9e7f54b86b4c0a9838b2c59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"13nvt7EFfApsRdRYn2JJZies0RMCH1mZedcVia+YEvRri2wJl++P9ZHcnBITiD7c6+O8jfCySiMhZATDvdFJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:28:26.522819Z","bundle_sha256":"0b1b1a2ec906bb45fffe3c0019af99ac1fe09ee082a3e7ca8f20b40840cab2c3"}}