{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FMZ6UB2UHYWWA4UDSPLATHK6IZ","short_pith_number":"pith:FMZ6UB2U","canonical_record":{"source":{"id":"2306.09303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:31:26Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"03fd1b5f6c58cddec8e27d16f8b8f08cfcc55b2c5896d4f2171847e24ca7fc37","abstract_canon_sha256":"99fbc8a16c15aedcba3e20db652e214efa8efa44aae6e121c9b05fb43590b40a"},"schema_version":"1.0"},"canonical_sha256":"2b33ea07543e2d60728393d6099d5e464a72c21642316f5155022dbc48ce93ab","source":{"kind":"arxiv","id":"2306.09303","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09303","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09303v2","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09303","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"pith_short_12","alias_value":"FMZ6UB2UHYWW","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"pith_short_16","alias_value":"FMZ6UB2UHYWWA4UD","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"pith_short_8","alias_value":"FMZ6UB2U","created_at":"2026-07-05T06:21:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FMZ6UB2UHYWWA4UDSPLATHK6IZ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:31:26Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"03fd1b5f6c58cddec8e27d16f8b8f08cfcc55b2c5896d4f2171847e24ca7fc37","abstract_canon_sha256":"99fbc8a16c15aedcba3e20db652e214efa8efa44aae6e121c9b05fb43590b40a"},"schema_version":"1.0"},"canonical_sha256":"2b33ea07543e2d60728393d6099d5e464a72c21642316f5155022dbc48ce93ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:18.397734Z","signature_b64":"Qv3VFeHIiW66zr6A8ibNlTxOxRlrQ7pda0rlf2bIGNPt/GusOolNwXnADj3msUoHVtJFJkj7h/4QJfEnqBW3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b33ea07543e2d60728393d6099d5e464a72c21642316f5155022dbc48ce93ab","last_reissued_at":"2026-07-05T06:21:18.397336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:18.397336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09303","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":"2026-07-05T06:21:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Ob45lqxU1kJZ5hXH1cscymdpKdko4S1klpxUUWEQhY052Z8r8XSk7soOi0k07efwu+ePy6M2ZFKnztNjVeiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:32:18.521816Z"},"content_sha256":"24cb5b56690bbf2f619ae40b1ccc15411297a47e0b8597602607aff9305d1342","schema_version":"1.0","event_id":"sha256:24cb5b56690bbf2f619ae40b1ccc15411297a47e0b8597602607aff9305d1342"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FMZ6UB2UHYWWA4UDSPLATHK6IZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Hanjiang Hu, Haohong Lin, Jiacheng Zhu, Jie Tan, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zijian Guo, Zuxin Liu","submitted_at":"2023-06-15T17:31:26Z","abstract_excerpt":"This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and deployment phases. Our benchmark suite contains three packages: 1) expertly crafted safe policies, 2) D4RL-styled datasets along with environment wrappers, and 3) high-quality offline safe RL baseline implementations. We feature a methodical data collection pipeline powered by advanced safe RL algorithms, which facilitates the generation of diverse datasets across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09303","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/2306.09303/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":"2026-07-05T06:21:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFe5sqEiwjSrSfAzRwpR8PGyo9NWC5zoHt6vupB/WXO4sJoK2CIUj4yBpOUEsGxPUkrexbOP3H4DUDnzVzbkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:32:18.522319Z"},"content_sha256":"886765c8cc5f3ae170f6498f827065342cdf55d1b9d04946cd7e847f8e2bc5e5","schema_version":"1.0","event_id":"sha256:886765c8cc5f3ae170f6498f827065342cdf55d1b9d04946cd7e847f8e2bc5e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ/bundle.json","state_url":"https://pith.science/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ/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":"2026-08-05T23:32:18Z","links":{"resolver":"https://pith.science/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ","bundle":"https://pith.science/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ/bundle.json","state":"https://pith.science/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMZ6UB2UHYWWA4UDSPLATHK6IZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FMZ6UB2UHYWWA4UDSPLATHK6IZ","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":"99fbc8a16c15aedcba3e20db652e214efa8efa44aae6e121c9b05fb43590b40a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:31:26Z","title_canon_sha256":"03fd1b5f6c58cddec8e27d16f8b8f08cfcc55b2c5896d4f2171847e24ca7fc37"},"schema_version":"1.0","source":{"id":"2306.09303","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09303","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09303v2","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09303","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"pith_short_12","alias_value":"FMZ6UB2UHYWW","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"pith_short_16","alias_value":"FMZ6UB2UHYWWA4UD","created_at":"2026-07-05T06:21:18Z"},{"alias_kind":"pith_short_8","alias_value":"FMZ6UB2U","created_at":"2026-07-05T06:21:18Z"}],"graph_snapshots":[{"event_id":"sha256:886765c8cc5f3ae170f6498f827065342cdf55d1b9d04946cd7e847f8e2bc5e5","target":"graph","created_at":"2026-07-05T06:21:18Z","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/2306.09303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and deployment phases. Our benchmark suite contains three packages: 1) expertly crafted safe policies, 2) D4RL-styled datasets along with environment wrappers, and 3) high-quality offline safe RL baseline implementations. We feature a methodical data collection pipeline powered by advanced safe RL algorithms, which facilitates the generation of diverse datasets across ","authors_text":"Ding Zhao, Hanjiang Hu, Haohong Lin, Jiacheng Zhu, Jie Tan, Tingnan Zhang, Wenhao Yu, Yihang Yao, 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":"2023-06-15T17:31:26Z","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09303","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":"sha256:24cb5b56690bbf2f619ae40b1ccc15411297a47e0b8597602607aff9305d1342","target":"record","created_at":"2026-07-05T06:21:18Z","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":"99fbc8a16c15aedcba3e20db652e214efa8efa44aae6e121c9b05fb43590b40a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:31:26Z","title_canon_sha256":"03fd1b5f6c58cddec8e27d16f8b8f08cfcc55b2c5896d4f2171847e24ca7fc37"},"schema_version":"1.0","source":{"id":"2306.09303","kind":"arxiv","version":2}},"canonical_sha256":"2b33ea07543e2d60728393d6099d5e464a72c21642316f5155022dbc48ce93ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b33ea07543e2d60728393d6099d5e464a72c21642316f5155022dbc48ce93ab","first_computed_at":"2026-07-05T06:21:18.397336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:18.397336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qv3VFeHIiW66zr6A8ibNlTxOxRlrQ7pda0rlf2bIGNPt/GusOolNwXnADj3msUoHVtJFJkj7h/4QJfEnqBW3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:18.397734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09303","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24cb5b56690bbf2f619ae40b1ccc15411297a47e0b8597602607aff9305d1342","sha256:886765c8cc5f3ae170f6498f827065342cdf55d1b9d04946cd7e847f8e2bc5e5"],"state_sha256":"1972749f77315df27e860cbf46f7616e5a580c1f11eadf8ebdbc7ec5bcd6a30b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jVveic7O502aI2/AAE1SLa2jxBvhSeDMwOZVHrfZ+V/9zS10ioeNehklUKEtSshitAObya/mojMzoq97fjeBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:32:18.527344Z","bundle_sha256":"95eee7b7e806ec5b61291367f4a03ab7c2748a20f8c152b65e8094a1053058e3"}}