{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G4ONBQPXTSZKNJW6WBS6XVB3HR","short_pith_number":"pith:G4ONBQPX","canonical_record":{"source":{"id":"2406.08406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"96c5b7f00bfb798f534ea08f84acdc45234f0ef16696a692919867b7f17d8f9b","abstract_canon_sha256":"6734a838b0a64a0ef19410b9154c16b8f36e58f4ecaee7fb9b668ae73799b8c9"},"schema_version":"1.0"},"canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","source":{"kind":"arxiv","id":"2406.08406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08406","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08406v1","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08406","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"G4ONBQPXTSZK","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"G4ONBQPXTSZKNJW6","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"G4ONBQPX","created_at":"2026-07-05T08:30:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G4ONBQPXTSZKNJW6WBS6XVB3HR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"96c5b7f00bfb798f534ea08f84acdc45234f0ef16696a692919867b7f17d8f9b","abstract_canon_sha256":"6734a838b0a64a0ef19410b9154c16b8f36e58f4ecaee7fb9b668ae73799b8c9"},"schema_version":"1.0"},"canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:59.294507Z","signature_b64":"iO1yLf8MGhazp/uqvQ9wedgqY35rkMubmBjHqyxgV+skaIrD7s02V83xujY7aMxSp/MP8gDAxmw3R1iRzA4SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","last_reissued_at":"2026-07-05T08:30:59.294023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:59.294023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08406","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":"2026-07-05T08:30:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mNVD3cr63OsQHMjkdNWYBYqN71UWBAzNm80lNTfLwDs6u0DX1YPtLvfiodCr7VF+bzVlFN7z931wEfJ1bgHdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:55:54.159327Z"},"content_sha256":"58dd7ceeda49a3324c282c93acef2bef1efc2e9a4bab4f0b64db9ba80a76334f","schema_version":"1.0","event_id":"sha256:58dd7ceeda49a3324c282c93acef2bef1efc2e9a4bab4f0b64db9ba80a76334f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G4ONBQPXTSZKNJW6WBS6XVB3HR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RRLS : Robust Reinforcement Learning Suite","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adil Zouitine, David Bertoin, Emmanuel Rachelson, Matthieu Geist, Pierre Clavier","submitted_at":"2024-06-12T16:53:51Z","abstract_excerpt":"Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two typ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08406","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/2406.08406/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":"2026-07-05T08:30:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OcxGyz1hiQGMQrCmXOvelTPdQ23FpcvnfVBMJIHoVXcRhQh22eKzaT1aXPGIk7jPCKunYKPUAoeCgz0be9ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:55:54.159881Z"},"content_sha256":"a6694310034824e2d0a7ca8c00775a7347db9944d9689299d5732c3800d35d42","schema_version":"1.0","event_id":"sha256:a6694310034824e2d0a7ca8c00775a7347db9944d9689299d5732c3800d35d42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/bundle.json","state_url":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/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":"2026-08-09T04:55:54Z","links":{"resolver":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR","bundle":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/bundle.json","state":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G4ONBQPXTSZKNJW6WBS6XVB3HR","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":"6734a838b0a64a0ef19410b9154c16b8f36e58f4ecaee7fb9b668ae73799b8c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:53:51Z","title_canon_sha256":"96c5b7f00bfb798f534ea08f84acdc45234f0ef16696a692919867b7f17d8f9b"},"schema_version":"1.0","source":{"id":"2406.08406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08406","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08406v1","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08406","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"G4ONBQPXTSZK","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"G4ONBQPXTSZKNJW6","created_at":"2026-07-05T08:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"G4ONBQPX","created_at":"2026-07-05T08:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:a6694310034824e2d0a7ca8c00775a7347db9944d9689299d5732c3800d35d42","target":"graph","created_at":"2026-07-05T08:30:59Z","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/2406.08406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two typ","authors_text":"Adil Zouitine, David Bertoin, Emmanuel Rachelson, Matthieu Geist, Pierre Clavier","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:53:51Z","title":"RRLS : Robust Reinforcement Learning Suite"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08406","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":"sha256:58dd7ceeda49a3324c282c93acef2bef1efc2e9a4bab4f0b64db9ba80a76334f","target":"record","created_at":"2026-07-05T08:30:59Z","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":"6734a838b0a64a0ef19410b9154c16b8f36e58f4ecaee7fb9b668ae73799b8c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:53:51Z","title_canon_sha256":"96c5b7f00bfb798f534ea08f84acdc45234f0ef16696a692919867b7f17d8f9b"},"schema_version":"1.0","source":{"id":"2406.08406","kind":"arxiv","version":1}},"canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","first_computed_at":"2026-07-05T08:30:59.294023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:59.294023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iO1yLf8MGhazp/uqvQ9wedgqY35rkMubmBjHqyxgV+skaIrD7s02V83xujY7aMxSp/MP8gDAxmw3R1iRzA4SDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:59.294507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58dd7ceeda49a3324c282c93acef2bef1efc2e9a4bab4f0b64db9ba80a76334f","sha256:a6694310034824e2d0a7ca8c00775a7347db9944d9689299d5732c3800d35d42"],"state_sha256":"4245d7e0e5b57eec70a244ea796f769bbb3f306e7747a0119f57abc3c910865f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgSnSFZu/gmRHqrdgr9OmgcqpsTQ4MQpCJyDx+zB0aijCCGl9x1nx2ngiQy74M4NTf/JJZ97vsE66c8USvL5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:55:54.167303Z","bundle_sha256":"bc50a9190cf4b9bc6f6d80bb6976822f6f9184409ea7dc3b9b306474919aadc9"}}