{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4NVSQWKUQE56LUKYPP6Y2JMCFI","short_pith_number":"pith:4NVSQWKU","canonical_record":{"source":{"id":"2212.00124","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T21:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"07864ef9291dc07f1272a3a066c61fae01593e022fef3f4fba6087113ad6e8e6","abstract_canon_sha256":"9fa3f1fb7f750ff23d3e8527de17bfa31952e6652e1289c6d9be3a75bc311b55"},"schema_version":"1.0"},"canonical_sha256":"e36b285954813be5d1587bfd8d25822a239de6309a4a5f8d34096b4a5d20b6f9","source":{"kind":"arxiv","id":"2212.00124","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00124","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00124v3","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00124","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"4NVSQWKUQE56","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"4NVSQWKUQE56LUKY","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"4NVSQWKU","created_at":"2026-07-05T07:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4NVSQWKUQE56LUKYPP6Y2JMCFI","target":"record","payload":{"canonical_record":{"source":{"id":"2212.00124","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T21:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"07864ef9291dc07f1272a3a066c61fae01593e022fef3f4fba6087113ad6e8e6","abstract_canon_sha256":"9fa3f1fb7f750ff23d3e8527de17bfa31952e6652e1289c6d9be3a75bc311b55"},"schema_version":"1.0"},"canonical_sha256":"e36b285954813be5d1587bfd8d25822a239de6309a4a5f8d34096b4a5d20b6f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:21.498027Z","signature_b64":"nFR1c65h+XpX5pw+O4NCijX/q5DyE0zekethvLsZFTj9PGAFJlYUtHTY4QqdjZJ0Ka9VQFBrjlBzZCRJm4uHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36b285954813be5d1587bfd8d25822a239de6309a4a5f8d34096b4a5d20b6f9","last_reissued_at":"2026-07-05T07:06:21.497650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:21.497650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.00124","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":"2026-07-05T07:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAZ4rlPsKli0UGrBdRVVB14PvS+22h6BAU33PlVpS/R0GKoKqO71O+/6o3xLjYD0bIrPTJga5lbTDrt2wxPoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:29:36.080918Z"},"content_sha256":"b490e4b073ac5e0a70cd10723fecfa16216546ccde130708a3ed7b43c7c24fe9","schema_version":"1.0","event_id":"sha256:b490e4b073ac5e0a70cd10723fecfa16216546ccde130708a3ed7b43c7c24fe9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4NVSQWKUQE56LUKYPP6Y2JMCFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bruno Lacerda, Marc Rigter, Nick Hawes","submitted_at":"2022-11-30T21:24:11Z","abstract_excerpt":"Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic outcomes. In other words, decision-making should be risk-sensitive. Previous works on risk in offline RL combine together offline RL techniques, to avoid distributional shift, with risk-sensitive RL algorithms, to achieve risk-sensitivity. In this work, we propose risk-sensitivity as a mechanism to jointly address both of these issues. Our model-based approach is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00124","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/2212.00124/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":"2026-07-05T07:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bPnVqTEEqL3yfGPPlgzdSOrBa7G+P3VywuicuGrFLKMffe5I4IE1JASuAKHzVrIY9iltum6jBwTxTKDL5aADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:29:36.081464Z"},"content_sha256":"73c55f204e9fa84e87f787e6b0d4d0eb60b725f6bc0e9c1ef1ec8ee37764511c","schema_version":"1.0","event_id":"sha256:73c55f204e9fa84e87f787e6b0d4d0eb60b725f6bc0e9c1ef1ec8ee37764511c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI/bundle.json","state_url":"https://pith.science/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI/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":"2026-08-19T06:29:36Z","links":{"resolver":"https://pith.science/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI","bundle":"https://pith.science/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI/bundle.json","state":"https://pith.science/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NVSQWKUQE56LUKYPP6Y2JMCFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4NVSQWKUQE56LUKYPP6Y2JMCFI","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":"9fa3f1fb7f750ff23d3e8527de17bfa31952e6652e1289c6d9be3a75bc311b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T21:24:11Z","title_canon_sha256":"07864ef9291dc07f1272a3a066c61fae01593e022fef3f4fba6087113ad6e8e6"},"schema_version":"1.0","source":{"id":"2212.00124","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00124","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00124v3","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00124","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"4NVSQWKUQE56","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"4NVSQWKUQE56LUKY","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"4NVSQWKU","created_at":"2026-07-05T07:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:73c55f204e9fa84e87f787e6b0d4d0eb60b725f6bc0e9c1ef1ec8ee37764511c","target":"graph","created_at":"2026-07-05T07:06:21Z","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/2212.00124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic outcomes. In other words, decision-making should be risk-sensitive. Previous works on risk in offline RL combine together offline RL techniques, to avoid distributional shift, with risk-sensitive RL algorithms, to achieve risk-sensitivity. In this work, we propose risk-sensitivity as a mechanism to jointly address both of these issues. Our model-based approach is","authors_text":"Bruno Lacerda, Marc Rigter, Nick Hawes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T21:24:11Z","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00124","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:b490e4b073ac5e0a70cd10723fecfa16216546ccde130708a3ed7b43c7c24fe9","target":"record","created_at":"2026-07-05T07:06:21Z","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":"9fa3f1fb7f750ff23d3e8527de17bfa31952e6652e1289c6d9be3a75bc311b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T21:24:11Z","title_canon_sha256":"07864ef9291dc07f1272a3a066c61fae01593e022fef3f4fba6087113ad6e8e6"},"schema_version":"1.0","source":{"id":"2212.00124","kind":"arxiv","version":3}},"canonical_sha256":"e36b285954813be5d1587bfd8d25822a239de6309a4a5f8d34096b4a5d20b6f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e36b285954813be5d1587bfd8d25822a239de6309a4a5f8d34096b4a5d20b6f9","first_computed_at":"2026-07-05T07:06:21.497650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:21.497650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nFR1c65h+XpX5pw+O4NCijX/q5DyE0zekethvLsZFTj9PGAFJlYUtHTY4QqdjZJ0Ka9VQFBrjlBzZCRJm4uHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:21.498027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00124","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b490e4b073ac5e0a70cd10723fecfa16216546ccde130708a3ed7b43c7c24fe9","sha256:73c55f204e9fa84e87f787e6b0d4d0eb60b725f6bc0e9c1ef1ec8ee37764511c"],"state_sha256":"bacb5909983aeb995fde47f4e420243542195d8d51bad1bc3eb124fe2354a1a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFaMouXUfbtGYjyoYZeZC1OreqQHhyM+qKTAl51erIJSZlM2nYD8t0fp2debsPYCP8MmyRqBYnXgLWo7bgJSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T06:29:36.086921Z","bundle_sha256":"a812f761327fbdfaa49d47197cc9f486b30ac69f42ae129b5e80601ce7336a1d"}}