{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZJMXG2AB2FOTSYMUCLPMCJXBVP","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":"8ba863c90221bb00cd6a3e391a60e9546d8033921cdb778ae87250b39fa8bc78","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-22T10:37:52Z","title_canon_sha256":"bfff8d04be94be975f810d885685b97677193d842989a45f8c0f44882c935a95"},"schema_version":"1.0","source":{"id":"2111.11097","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11097","created_at":"2026-07-05T04:35:09Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11097v3","created_at":"2026-07-05T04:35:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11097","created_at":"2026-07-05T04:35:09Z"},{"alias_kind":"pith_short_12","alias_value":"ZJMXG2AB2FOT","created_at":"2026-07-05T04:35:09Z"},{"alias_kind":"pith_short_16","alias_value":"ZJMXG2AB2FOTSYMU","created_at":"2026-07-05T04:35:09Z"},{"alias_kind":"pith_short_8","alias_value":"ZJMXG2AB","created_at":"2026-07-05T04:35:09Z"}],"graph_snapshots":[{"event_id":"sha256:24bffa26e92fe486c9f359cf84bbab6abc2a40c4ccca1432fa5b9d9a621062b9","target":"graph","created_at":"2026-07-05T04:35:09Z","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/2111.11097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) provides a framework for learning decision-making from offline data and therefore constitutes a promising approach for real-world applications as automated driving. Self-driving vehicles (SDV) learn a policy, which potentially even outperforms the behavior in the sub-optimal data set. Especially in safety-critical applications as automated driving, explainability and transferability are key to success. This motivates the use of model-based offline RL approaches, which leverage planning. However, current state-of-the-art methods often neglect the influence of","authors_text":"Christopher Diehl, Frank Hoffmann, Martin Kr\\\"uger, Timo Sievernich, Torsten Bertram","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-22T10:37:52Z","title":"UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11097","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":"sha256:4f41cdee3144e166b322e269d824961d83a87af387b7c10243d32b0723017d7b","target":"record","created_at":"2026-07-05T04:35:09Z","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":"8ba863c90221bb00cd6a3e391a60e9546d8033921cdb778ae87250b39fa8bc78","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-22T10:37:52Z","title_canon_sha256":"bfff8d04be94be975f810d885685b97677193d842989a45f8c0f44882c935a95"},"schema_version":"1.0","source":{"id":"2111.11097","kind":"arxiv","version":3}},"canonical_sha256":"ca59736801d15d39619412dec126e1abf8bcaf0484069c82f171f2ac144ce0b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca59736801d15d39619412dec126e1abf8bcaf0484069c82f171f2ac144ce0b8","first_computed_at":"2026-07-05T04:35:09.757606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:35:09.757606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vRifko/RD8MNpD+nPvc4ZXPbUvU9vdCdT4zygtwqhDL27z0DD+2tTpSsyjkX8sKORx65XcqHtmaquExUhsO8DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:35:09.758054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11097","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f41cdee3144e166b322e269d824961d83a87af387b7c10243d32b0723017d7b","sha256:24bffa26e92fe486c9f359cf84bbab6abc2a40c4ccca1432fa5b9d9a621062b9"],"state_sha256":"83b9478d2fa04b3518701bb996c4c410bf1371d018f1b0370c39e5a8b11bd2af"}