{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3T5HLDQQKTUBFO7N2N73A3IONY","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":"ee0ca840467edfe06494798c608719e5bf6f571b768a58188ca852138aee5625","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T13:51:34Z","title_canon_sha256":"322ebb18e1b6d20c8ec296d68d7ba94ad54fcee7ce0e7f975e6dc6a71aebf2cb"},"schema_version":"1.0","source":{"id":"2110.04135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04135","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04135v2","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04135","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"3T5HLDQQKTUB","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"3T5HLDQQKTUBFO7N","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"3T5HLDQQ","created_at":"2026-07-05T04:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:8ddb5cc7170b56bcb7bc894337032f419167fd0f4dfdffc1b1fc1ed26cc8b261","target":"graph","created_at":"2026-07-05T04:05:35Z","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/2110.04135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant progress has been made recently in offline model-based reinforcement learning, approaches which leverage a learned dynamics model. This typically involves constructing a probabilistic model, and using the model uncertainty to penalize rewards where there is insufficient data, solving for a pessimistic MDP that lower bounds the true MDP. Existing methods, however","authors_text":"Cong Lu, Jack Parker-Holder, Michael A. Osborne, Philip J. Ball, Stephen J. Roberts","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T13:51:34Z","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04135","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":"sha256:0ee2cce2d9e2b93486a7e21debc6fb9e284217e49eaa1605987cd2a68a0e4a01","target":"record","created_at":"2026-07-05T04:05:35Z","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":"ee0ca840467edfe06494798c608719e5bf6f571b768a58188ca852138aee5625","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T13:51:34Z","title_canon_sha256":"322ebb18e1b6d20c8ec296d68d7ba94ad54fcee7ce0e7f975e6dc6a71aebf2cb"},"schema_version":"1.0","source":{"id":"2110.04135","kind":"arxiv","version":2}},"canonical_sha256":"dcfa758e1054e812bbedd37fb06d0e6e3acc053c3d59e281a0e4ef4186edba40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcfa758e1054e812bbedd37fb06d0e6e3acc053c3d59e281a0e4ef4186edba40","first_computed_at":"2026-07-05T04:05:35.510655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:35.510655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mXygTZ1sKNzIbVcFbb1CNWfhNn2Tu16f0a8lRtPQEW8rZRjVsQa5nLnD2+gCEDYGEqj7Qums9gTBcZPa8SFiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:35.511092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ee2cce2d9e2b93486a7e21debc6fb9e284217e49eaa1605987cd2a68a0e4a01","sha256:8ddb5cc7170b56bcb7bc894337032f419167fd0f4dfdffc1b1fc1ed26cc8b261"],"state_sha256":"998c0726fde187a644d1b670f9c0688393586b03a7e3dc933355c994d0166c34"}