{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LP7XIXLIUGNOKJ6EORBQH2I3V5","short_pith_number":"pith:LP7XIXLI","canonical_record":{"source":{"id":"2305.03360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T08:23:56Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"96b613790a536060dbde7aeb76057b7bcd5077221bac5c8bfe9634fe3694e6eb","abstract_canon_sha256":"90dbd8493943fffeaf5e38feab86400beaa7a89eb219243744d17b11c0375597"},"schema_version":"1.0"},"canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","source":{"kind":"arxiv","id":"2305.03360","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03360","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03360v1","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03360","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"LP7XIXLIUGNO","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"LP7XIXLIUGNOKJ6E","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"LP7XIXLI","created_at":"2026-07-05T06:07:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LP7XIXLIUGNOKJ6EORBQH2I3V5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T08:23:56Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"96b613790a536060dbde7aeb76057b7bcd5077221bac5c8bfe9634fe3694e6eb","abstract_canon_sha256":"90dbd8493943fffeaf5e38feab86400beaa7a89eb219243744d17b11c0375597"},"schema_version":"1.0"},"canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:22.444395Z","signature_b64":"I45mCvJZ4beY0n1xHQjSmmugTIN1LNw136PvfCYGFP2D5DH69UiS5WpBDs5/3QwVfK75OU+R3ADLXQDfBcicCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","last_reissued_at":"2026-07-05T06:07:22.444003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:22.444003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03360","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":"2026-07-05T06:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MnqiAy0olGEMzs58pu204YNLVPIBUCZ2D3UHcNoDRc/jGevhzGvhBitLPuk4tWQTgBXRSrEXnqJjworJOqr8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:14:28.670848Z"},"content_sha256":"75b676519e05e25da8c6525f23e6b201b6268d9cc09640cfb9140ada18ffbf8b","schema_version":"1.0","event_id":"sha256:75b676519e05e25da8c6525f23e6b201b6268d9cc09640cfb9140ada18ffbf8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LP7XIXLIUGNOKJ6EORBQH2I3V5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Offline Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Haoyang He","submitted_at":"2023-05-05T08:23:56Z","abstract_excerpt":"Model-based approaches are becoming increasingly popular in the field of offline reinforcement learning, with high potential in real-world applications due to the model's capability of thoroughly utilizing the large historical datasets available with supervised learning techniques. This paper presents a literature review of recent work in offline model-based reinforcement learning, a field that utilizes model-based approaches in offline reinforcement learning. The survey provides a brief overview of the concepts and recent developments in both offline reinforcement learning and model-based rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03360","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/2305.03360/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":"2026-07-05T06:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OnCCT0sfjlLTiZoA8OY8wWXMZXBkrE2GQgUnQEoEKLSe7PRTvkc+Dyi8UZPV/WCAusQsNnxPzy85oZxG0PueCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:14:28.671234Z"},"content_sha256":"c8cf3df079fde1003c69a4b5202ba248eb87f6f11e2f0b7c7063aad0f5d45b20","schema_version":"1.0","event_id":"sha256:c8cf3df079fde1003c69a4b5202ba248eb87f6f11e2f0b7c7063aad0f5d45b20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/bundle.json","state_url":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/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":"2026-08-06T07:14:28Z","links":{"resolver":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5","bundle":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/bundle.json","state":"https://pith.science/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LP7XIXLIUGNOKJ6EORBQH2I3V5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LP7XIXLIUGNOKJ6EORBQH2I3V5","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":"90dbd8493943fffeaf5e38feab86400beaa7a89eb219243744d17b11c0375597","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T08:23:56Z","title_canon_sha256":"96b613790a536060dbde7aeb76057b7bcd5077221bac5c8bfe9634fe3694e6eb"},"schema_version":"1.0","source":{"id":"2305.03360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03360","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03360v1","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03360","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"LP7XIXLIUGNO","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"LP7XIXLIUGNOKJ6E","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"LP7XIXLI","created_at":"2026-07-05T06:07:22Z"}],"graph_snapshots":[{"event_id":"sha256:c8cf3df079fde1003c69a4b5202ba248eb87f6f11e2f0b7c7063aad0f5d45b20","target":"graph","created_at":"2026-07-05T06:07:22Z","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/2305.03360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based approaches are becoming increasingly popular in the field of offline reinforcement learning, with high potential in real-world applications due to the model's capability of thoroughly utilizing the large historical datasets available with supervised learning techniques. This paper presents a literature review of recent work in offline model-based reinforcement learning, a field that utilizes model-based approaches in offline reinforcement learning. The survey provides a brief overview of the concepts and recent developments in both offline reinforcement learning and model-based rei","authors_text":"Haoyang He","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T08:23:56Z","title":"A Survey on Offline Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03360","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":"sha256:75b676519e05e25da8c6525f23e6b201b6268d9cc09640cfb9140ada18ffbf8b","target":"record","created_at":"2026-07-05T06:07:22Z","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":"90dbd8493943fffeaf5e38feab86400beaa7a89eb219243744d17b11c0375597","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-05T08:23:56Z","title_canon_sha256":"96b613790a536060dbde7aeb76057b7bcd5077221bac5c8bfe9634fe3694e6eb"},"schema_version":"1.0","source":{"id":"2305.03360","kind":"arxiv","version":1}},"canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bff745d68a19ae527c4744303e91baf5a63c8e6342b57f5089fe707764d5241","first_computed_at":"2026-07-05T06:07:22.444003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:22.444003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I45mCvJZ4beY0n1xHQjSmmugTIN1LNw136PvfCYGFP2D5DH69UiS5WpBDs5/3QwVfK75OU+R3ADLXQDfBcicCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:22.444395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75b676519e05e25da8c6525f23e6b201b6268d9cc09640cfb9140ada18ffbf8b","sha256:c8cf3df079fde1003c69a4b5202ba248eb87f6f11e2f0b7c7063aad0f5d45b20"],"state_sha256":"b27de644acb0661f1b663ace2f1521c1f00bed1510be23f992730938a02979e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M4fYBOF0i0JwiPczMpL+/Uja6HA8+7jgQQoCHOeLeHNGlvC10P3CYHiuVfDhmBkS0YxeWt/UCV+H5lqGyxleDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:14:28.675177Z","bundle_sha256":"ac30c0840df7121311bed659779922162feba472924482378987c57b7a28ac2c"}}