{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NNPKIIWLOJ7UPO6Q57AZTXLE34","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":"3c7cb82cdd8e43631b2ff3ee09c2872c8b205dd54236533e3eed66758cdb0dea","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-19T08:19:28Z","title_canon_sha256":"f42d32dd7c1c0bd8aa42474d9da3a02b10db1515411d8f69ac189fabd1841cce"},"schema_version":"1.0","source":{"id":"2310.12567","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12567","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12567v3","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12567","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"NNPKIIWLOJ7U","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"NNPKIIWLOJ7UPO6Q","created_at":"2026-07-05T09:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"NNPKIIWL","created_at":"2026-07-05T09:16:09Z"}],"graph_snapshots":[{"event_id":"sha256:fafb2b4daad3ab40675c6dafebc6896ad42df0cafc127bc59c228b35fdd7ac41","target":"graph","created_at":"2026-07-05T09:16:09Z","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/2310.12567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-onl","authors_text":"Borong Zhang, Jiaming Ji, Jiayi Zhou, Juntao Dai, Ruiyang Sun, Weidong Huang, Xuehai Pan, Yaodong Yang, Yifan Zhong, Yiran Geng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-19T08:19:28Z","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12567","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":"sha256:22f4fcbcc04b98e02aad3b192759ee782f55d52d5e54a4decf6f6dbd0d280997","target":"record","created_at":"2026-07-05T09:16:09Z","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":"3c7cb82cdd8e43631b2ff3ee09c2872c8b205dd54236533e3eed66758cdb0dea","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-19T08:19:28Z","title_canon_sha256":"f42d32dd7c1c0bd8aa42474d9da3a02b10db1515411d8f69ac189fabd1841cce"},"schema_version":"1.0","source":{"id":"2310.12567","kind":"arxiv","version":3}},"canonical_sha256":"6b5ea422cb727f47bbd0efc199dd64df0e692aa400ef9d5f5a791ff18f3f1f24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b5ea422cb727f47bbd0efc199dd64df0e692aa400ef9d5f5a791ff18f3f1f24","first_computed_at":"2026-07-05T09:16:09.613496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:09.613496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OlWK32Z0yB90qyf19H++Uy+Jd69sjU8FNd/HxHm1YqrVpox1SeS1+PdM8KvHYHILgeB5l+xcTMy3bSBjFqOoAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:09.614014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12567","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22f4fcbcc04b98e02aad3b192759ee782f55d52d5e54a4decf6f6dbd0d280997","sha256:fafb2b4daad3ab40675c6dafebc6896ad42df0cafc127bc59c228b35fdd7ac41"],"state_sha256":"6be9a7c812f2591dfedb2a7744c4d1566a01ab313a7e5927dfed6519330c5c0f"}