{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KFEOVFFXW434HLVHEZHQ7M4E5K","short_pith_number":"pith:KFEOVFFX","canonical_record":{"source":{"id":"2205.14691","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T15:25:03Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fb8b4402f6f938fb3c923b080618e1bda0cadd7982bb2797ad4cbb0c9e97904d","abstract_canon_sha256":"b7112489d218529d8e892e40045bac90423b0d3abcfe80323ff29543e3eb3d63"},"schema_version":"1.0"},"canonical_sha256":"5148ea94b7b737c3aea7264f0fb384eaad7b9cf89bfdfc0ae615bee718551264","source":{"kind":"arxiv","id":"2205.14691","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14691","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14691v3","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14691","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"KFEOVFFXW434","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"KFEOVFFXW434HLVH","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"KFEOVFFX","created_at":"2026-07-05T05:47:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KFEOVFFXW434HLVHEZHQ7M4E5K","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14691","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T15:25:03Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fb8b4402f6f938fb3c923b080618e1bda0cadd7982bb2797ad4cbb0c9e97904d","abstract_canon_sha256":"b7112489d218529d8e892e40045bac90423b0d3abcfe80323ff29543e3eb3d63"},"schema_version":"1.0"},"canonical_sha256":"5148ea94b7b737c3aea7264f0fb384eaad7b9cf89bfdfc0ae615bee718551264","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:15.706357Z","signature_b64":"FYBQCQ83OWrRKNZC132MqmWXmmIQkLaWEClEHPUf0M7EPdqX8MUDPsn+eNmFWz4aJ8cNkz0e2C7zTEL+m5F7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5148ea94b7b737c3aea7264f0fb384eaad7b9cf89bfdfc0ae615bee718551264","last_reissued_at":"2026-07-05T05:47:15.705823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:15.705823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14691","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":"2026-07-05T05:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jyR+RcKk6fWViaEBfJpFkefj37kV3isB0ETij5RHQoHRLGI/iFqS9BOH5r6XDFYXz4PDUFhIAVDWF8Iv3JDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:50:52.716715Z"},"content_sha256":"860e020643f0ff4834bdc0c31f4e6aa51c2649bcfcf9a384c2f2eae7935f7122","schema_version":"1.0","event_id":"sha256:860e020643f0ff4834bdc0c31f4e6aa51c2649bcfcf9a384c2f2eae7935f7122"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KFEOVFFXW434HLVHEZHQ7M4E5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bo Li, Ding Zhao, Huan Zhang, Jie Tan, Zhepeng Cen, Zijian Guo, Zuxin Liu","submitted_at":"2022-05-29T15:25:03Z","abstract_excerpt":"Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not robust and safe against carefully designed observational perturbations. We formally analyze the unique properties of designing effective observational adversarial attackers in the safe RL setting. We show that baseline adversarial attack techniques for standard RL tasks are not always effective for safe RL and propose two new approaches - one maximizes the cost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14691","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/2205.14691/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":"2026-07-05T05:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSC2vdjOyivxPzpHjx28EzgJtXN2CYeehPmrm4wHUWs1KEY1mgr2LS5nxv1A33aHvt6EkzTD1prBQIKY7AqjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:50:52.717617Z"},"content_sha256":"33109cd612ebfc322ca55036839173daa0b623911270b19509e0b813ae36bfcd","schema_version":"1.0","event_id":"sha256:33109cd612ebfc322ca55036839173daa0b623911270b19509e0b813ae36bfcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFEOVFFXW434HLVHEZHQ7M4E5K/bundle.json","state_url":"https://pith.science/pith/KFEOVFFXW434HLVHEZHQ7M4E5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFEOVFFXW434HLVHEZHQ7M4E5K/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":"2026-08-06T04:50:52Z","links":{"resolver":"https://pith.science/pith/KFEOVFFXW434HLVHEZHQ7M4E5K","bundle":"https://pith.science/pith/KFEOVFFXW434HLVHEZHQ7M4E5K/bundle.json","state":"https://pith.science/pith/KFEOVFFXW434HLVHEZHQ7M4E5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFEOVFFXW434HLVHEZHQ7M4E5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KFEOVFFXW434HLVHEZHQ7M4E5K","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":"b7112489d218529d8e892e40045bac90423b0d3abcfe80323ff29543e3eb3d63","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T15:25:03Z","title_canon_sha256":"fb8b4402f6f938fb3c923b080618e1bda0cadd7982bb2797ad4cbb0c9e97904d"},"schema_version":"1.0","source":{"id":"2205.14691","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14691","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14691v3","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14691","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"KFEOVFFXW434","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"KFEOVFFXW434HLVH","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"KFEOVFFX","created_at":"2026-07-05T05:47:15Z"}],"graph_snapshots":[{"event_id":"sha256:33109cd612ebfc322ca55036839173daa0b623911270b19509e0b813ae36bfcd","target":"graph","created_at":"2026-07-05T05:47:15Z","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/2205.14691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not robust and safe against carefully designed observational perturbations. We formally analyze the unique properties of designing effective observational adversarial attackers in the safe RL setting. We show that baseline adversarial attack techniques for standard RL tasks are not always effective for safe RL and propose two new approaches - one maximizes the cost","authors_text":"Bo Li, Ding Zhao, Huan Zhang, Jie Tan, Zhepeng Cen, Zijian Guo, Zuxin Liu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T15:25:03Z","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14691","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":"sha256:860e020643f0ff4834bdc0c31f4e6aa51c2649bcfcf9a384c2f2eae7935f7122","target":"record","created_at":"2026-07-05T05:47:15Z","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":"b7112489d218529d8e892e40045bac90423b0d3abcfe80323ff29543e3eb3d63","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T15:25:03Z","title_canon_sha256":"fb8b4402f6f938fb3c923b080618e1bda0cadd7982bb2797ad4cbb0c9e97904d"},"schema_version":"1.0","source":{"id":"2205.14691","kind":"arxiv","version":3}},"canonical_sha256":"5148ea94b7b737c3aea7264f0fb384eaad7b9cf89bfdfc0ae615bee718551264","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5148ea94b7b737c3aea7264f0fb384eaad7b9cf89bfdfc0ae615bee718551264","first_computed_at":"2026-07-05T05:47:15.705823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:15.705823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FYBQCQ83OWrRKNZC132MqmWXmmIQkLaWEClEHPUf0M7EPdqX8MUDPsn+eNmFWz4aJ8cNkz0e2C7zTEL+m5F7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:15.706357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14691","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:860e020643f0ff4834bdc0c31f4e6aa51c2649bcfcf9a384c2f2eae7935f7122","sha256:33109cd612ebfc322ca55036839173daa0b623911270b19509e0b813ae36bfcd"],"state_sha256":"3d04abf2c707c15023e390ca0ca6136552ebfbbf3d77f4cd1983e5c94fe937b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"coc69bIKmYyuLMZacFq2bN/y+amqwnKtWitLpJettLzWkOGjwhMfcuevlT2NeytIWnCHqISQGrAHucMDjEmjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:50:52.722863Z","bundle_sha256":"efa87cb47f951da25df369e9f0ff4da14ddf9ab6fbeff8ff4e3d59ab32d608f1"}}