{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3T5HLDQQKTUBFO7N2N73A3IONY","short_pith_number":"pith:3T5HLDQQ","canonical_record":{"source":{"id":"2110.04135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T13:51:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"322ebb18e1b6d20c8ec296d68d7ba94ad54fcee7ce0e7f975e6dc6a71aebf2cb","abstract_canon_sha256":"ee0ca840467edfe06494798c608719e5bf6f571b768a58188ca852138aee5625"},"schema_version":"1.0"},"canonical_sha256":"dcfa758e1054e812bbedd37fb06d0e6e3acc053c3d59e281a0e4ef4186edba40","source":{"kind":"arxiv","id":"2110.04135","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3T5HLDQQKTUBFO7N2N73A3IONY","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T13:51:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"322ebb18e1b6d20c8ec296d68d7ba94ad54fcee7ce0e7f975e6dc6a71aebf2cb","abstract_canon_sha256":"ee0ca840467edfe06494798c608719e5bf6f571b768a58188ca852138aee5625"},"schema_version":"1.0"},"canonical_sha256":"dcfa758e1054e812bbedd37fb06d0e6e3acc053c3d59e281a0e4ef4186edba40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:35.511092Z","signature_b64":"mXygTZ1sKNzIbVcFbb1CNWfhNn2Tu16f0a8lRtPQEW8rZRjVsQa5nLnD2+gCEDYGEqj7Qums9gTBcZPa8SFiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcfa758e1054e812bbedd37fb06d0e6e3acc053c3d59e281a0e4ef4186edba40","last_reissued_at":"2026-07-05T04:05:35.510655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:35.510655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04135","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":"2026-07-05T04:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8i7GQxxGhXZBgn0A91LQta6zmfjTPlHYdfp2j0/LNMDx86uCHCHeVf8peAnyFJUHMrJ7IJEli9QRcWbavvBuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:32:23.585511Z"},"content_sha256":"0ee2cce2d9e2b93486a7e21debc6fb9e284217e49eaa1605987cd2a68a0e4a01","schema_version":"1.0","event_id":"sha256:0ee2cce2d9e2b93486a7e21debc6fb9e284217e49eaa1605987cd2a68a0e4a01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3T5HLDQQKTUBFO7N2N73A3IONY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cong Lu, Jack Parker-Holder, Michael A. Osborne, Philip J. Ball, Stephen J. Roberts","submitted_at":"2021-10-08T13:51:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04135","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/2110.04135/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":"2026-07-05T04:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4eIhxXBM+Xcl/qnKdodb0aHJV5pKdvqHq0Y6LouEVMc9ZajbpER1hKtUARomEe/FuhHvVJdwc1ehZUd9oUuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:32:23.586049Z"},"content_sha256":"8ddb5cc7170b56bcb7bc894337032f419167fd0f4dfdffc1b1fc1ed26cc8b261","schema_version":"1.0","event_id":"sha256:8ddb5cc7170b56bcb7bc894337032f419167fd0f4dfdffc1b1fc1ed26cc8b261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3T5HLDQQKTUBFO7N2N73A3IONY/bundle.json","state_url":"https://pith.science/pith/3T5HLDQQKTUBFO7N2N73A3IONY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3T5HLDQQKTUBFO7N2N73A3IONY/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":"2026-08-15T19:32:23Z","links":{"resolver":"https://pith.science/pith/3T5HLDQQKTUBFO7N2N73A3IONY","bundle":"https://pith.science/pith/3T5HLDQQKTUBFO7N2N73A3IONY/bundle.json","state":"https://pith.science/pith/3T5HLDQQKTUBFO7N2N73A3IONY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3T5HLDQQKTUBFO7N2N73A3IONY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dMRu/NyngsWg+dk93z7gCzYI6Tkc8x5ReY8HGOm5qYdB0lt9k1eLEmxQ6e94kpOLH23HbudOLaY6FUNrdaFDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:32:23.589598Z","bundle_sha256":"f0a70c9adb10e156e351d89ff561fede6e1d96c0e2fcee20cd14d8b295091d24"}}