{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FQOLMSCU2WQ73TET6TIXUXSTBO","short_pith_number":"pith:FQOLMSCU","canonical_record":{"source":{"id":"2305.09304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T09:22:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae59beb4ac9b81baffab1f25cfbd4d98b87c62b175bfb4d840ef0098b7508294","abstract_canon_sha256":"1abd95af8502a4a32288f792e80344b9962208e82c3f3905bbd5d16feccb458d"},"schema_version":"1.0"},"canonical_sha256":"2c1cb64854d5a1fdcc93f4d17a5e530b8ba5799ccb35bf13ebd7cc8843bde016","source":{"kind":"arxiv","id":"2305.09304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09304","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09304v1","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09304","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"FQOLMSCU2WQ7","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"pith_short_16","alias_value":"FQOLMSCU2WQ73TET","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"pith_short_8","alias_value":"FQOLMSCU","created_at":"2026-07-05T06:10:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FQOLMSCU2WQ73TET6TIXUXSTBO","target":"record","payload":{"canonical_record":{"source":{"id":"2305.09304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T09:22:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae59beb4ac9b81baffab1f25cfbd4d98b87c62b175bfb4d840ef0098b7508294","abstract_canon_sha256":"1abd95af8502a4a32288f792e80344b9962208e82c3f3905bbd5d16feccb458d"},"schema_version":"1.0"},"canonical_sha256":"2c1cb64854d5a1fdcc93f4d17a5e530b8ba5799ccb35bf13ebd7cc8843bde016","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:46.574497Z","signature_b64":"sA3RACxoL1oQAFjyQkYw/hMjIo0XBvKvNDHoCnA6cJvPYVKJGU+qEknZHATlki85gXsE22SvCdk9PXb/dACoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1cb64854d5a1fdcc93f4d17a5e530b8ba5799ccb35bf13ebd7cc8843bde016","last_reissued_at":"2026-07-05T06:10:46.574038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:46.574038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.09304","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":"2026-07-05T06:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnVydre+EmIWXMo49c7Sz269G63OEJJZSw6Xf/W6Fsd4+FJxtUtDMA0dkFWhz33httTORjwWdeuzY6U6VHDJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:28:44.725597Z"},"content_sha256":"e841a898df8fdc8cbc7903d40c25a82836877583a01752dc58e4564933295f4b","schema_version":"1.0","event_id":"sha256:e841a898df8fdc8cbc7903d40c25a82836877583a01752dc58e4564933295f4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FQOLMSCU2WQ73TET6TIXUXSTBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Borong Zhang, Jiaming Ji, Jiayi Zhou, Juntao Dai, Mickel Liu, Ruiyang Sun, Weidong Huang, Xuehai Pan, Yaodong Yang, Yiran Geng","submitted_at":"2023-05-16T09:22:14Z","abstract_excerpt":"AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical applications, researchers have raised concerns about unintended harms or unsafe behaviors of unaligned RL agents. The philosophy of safe reinforcement learning (SafeRL) is to align RL agents with harmless intentions and safe behavioral patterns. In SafeRL, agents learn to develop optimal policies by receiving feedback from the environment, while also fulfilling the requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09304","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/2305.09304/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":"2026-07-05T06:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tcD8WP9bU+7qmHi09Jo6TBMfUnzPGQbt3Frv9XWjcUm+Gja5FHnbY3geCINwazIeW80TgFLnufmq65cToSs6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:28:44.726505Z"},"content_sha256":"c638c5cd78038c5c6bfaa731590a6aac40e9529d8729b74003f08aaa8e079fe2","schema_version":"1.0","event_id":"sha256:c638c5cd78038c5c6bfaa731590a6aac40e9529d8729b74003f08aaa8e079fe2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQOLMSCU2WQ73TET6TIXUXSTBO/bundle.json","state_url":"https://pith.science/pith/FQOLMSCU2WQ73TET6TIXUXSTBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQOLMSCU2WQ73TET6TIXUXSTBO/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":"2026-08-13T11:28:44Z","links":{"resolver":"https://pith.science/pith/FQOLMSCU2WQ73TET6TIXUXSTBO","bundle":"https://pith.science/pith/FQOLMSCU2WQ73TET6TIXUXSTBO/bundle.json","state":"https://pith.science/pith/FQOLMSCU2WQ73TET6TIXUXSTBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQOLMSCU2WQ73TET6TIXUXSTBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FQOLMSCU2WQ73TET6TIXUXSTBO","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":"1abd95af8502a4a32288f792e80344b9962208e82c3f3905bbd5d16feccb458d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T09:22:14Z","title_canon_sha256":"ae59beb4ac9b81baffab1f25cfbd4d98b87c62b175bfb4d840ef0098b7508294"},"schema_version":"1.0","source":{"id":"2305.09304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09304","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09304v1","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09304","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"FQOLMSCU2WQ7","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"pith_short_16","alias_value":"FQOLMSCU2WQ73TET","created_at":"2026-07-05T06:10:46Z"},{"alias_kind":"pith_short_8","alias_value":"FQOLMSCU","created_at":"2026-07-05T06:10:46Z"}],"graph_snapshots":[{"event_id":"sha256:c638c5cd78038c5c6bfaa731590a6aac40e9529d8729b74003f08aaa8e079fe2","target":"graph","created_at":"2026-07-05T06:10:46Z","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/2305.09304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical applications, researchers have raised concerns about unintended harms or unsafe behaviors of unaligned RL agents. The philosophy of safe reinforcement learning (SafeRL) is to align RL agents with harmless intentions and safe behavioral patterns. In SafeRL, agents learn to develop optimal policies by receiving feedback from the environment, while also fulfilling the requ","authors_text":"Borong Zhang, Jiaming Ji, Jiayi Zhou, Juntao Dai, Mickel Liu, Ruiyang Sun, Weidong Huang, Xuehai Pan, Yaodong Yang, Yiran Geng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T09:22:14Z","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09304","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:e841a898df8fdc8cbc7903d40c25a82836877583a01752dc58e4564933295f4b","target":"record","created_at":"2026-07-05T06:10:46Z","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":"1abd95af8502a4a32288f792e80344b9962208e82c3f3905bbd5d16feccb458d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T09:22:14Z","title_canon_sha256":"ae59beb4ac9b81baffab1f25cfbd4d98b87c62b175bfb4d840ef0098b7508294"},"schema_version":"1.0","source":{"id":"2305.09304","kind":"arxiv","version":1}},"canonical_sha256":"2c1cb64854d5a1fdcc93f4d17a5e530b8ba5799ccb35bf13ebd7cc8843bde016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c1cb64854d5a1fdcc93f4d17a5e530b8ba5799ccb35bf13ebd7cc8843bde016","first_computed_at":"2026-07-05T06:10:46.574038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:10:46.574038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sA3RACxoL1oQAFjyQkYw/hMjIo0XBvKvNDHoCnA6cJvPYVKJGU+qEknZHATlki85gXsE22SvCdk9PXb/dACoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:10:46.574497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e841a898df8fdc8cbc7903d40c25a82836877583a01752dc58e4564933295f4b","sha256:c638c5cd78038c5c6bfaa731590a6aac40e9529d8729b74003f08aaa8e079fe2"],"state_sha256":"48ea7b5230d27eaddf62a12c7283eb4869f1dd1cd750270ef77eed02ea80e027"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yZWTljsXmQVUE+s5ur5ePKRQNFJ1uwfwQbZEyiILb6vVjPq9xyoJlrVbviWUfFgSeXNQAJL2GkiXy1P/0sbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:28:44.740002Z","bundle_sha256":"c6c064b5acaa30457d88828f4f3a23a1964330028a653293eae16c498ebc9fc9"}}