{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5UCBUQ277IRIJIJQWQEH7KIRB5","short_pith_number":"pith:5UCBUQ27","canonical_record":{"source":{"id":"2309.08925","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-16T08:39:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6aa9fb3d51f29352ead2740bc4b883280539653599cf46d8c56316c50298957c","abstract_canon_sha256":"705a235ca5b49748bd3896f34e5b5940c80ec8b581bcc2bf0d8f074a7c99d4b5"},"schema_version":"1.0"},"canonical_sha256":"ed041a435ffa2284a130b4087fa9110f58fbb500e1a608459f722748c2bb8f4d","source":{"kind":"arxiv","id":"2309.08925","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08925","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08925v4","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08925","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"5UCBUQ277IRI","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"5UCBUQ277IRIJIJQ","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"5UCBUQ27","created_at":"2026-07-05T11:18:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5UCBUQ277IRIJIJQWQEH7KIRB5","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08925","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-16T08:39:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6aa9fb3d51f29352ead2740bc4b883280539653599cf46d8c56316c50298957c","abstract_canon_sha256":"705a235ca5b49748bd3896f34e5b5940c80ec8b581bcc2bf0d8f074a7c99d4b5"},"schema_version":"1.0"},"canonical_sha256":"ed041a435ffa2284a130b4087fa9110f58fbb500e1a608459f722748c2bb8f4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:10.574822Z","signature_b64":"ysSigbtMvdHIPKrNyZoQum3E1j2iHiC4whEftc8Y+CCzaIFg6zMXws3TbIKtGpF302Gu1VrZnG7eOOSTFB7/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed041a435ffa2284a130b4087fa9110f58fbb500e1a608459f722748c2bb8f4d","last_reissued_at":"2026-07-05T11:18:10.574394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:10.574394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08925","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0KAZNNqn3E3eu5v5nMrKptnOUO6k4KnqnIw6SBf4QYowqvs44XrsKoOu8iMnZlDqkF59KnDymDtCXLg3buDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:18:23.508958Z"},"content_sha256":"243561d0af30e17aafb976989f1189ab670d79585b2829f5fdd6f40157f49438","schema_version":"1.0","event_id":"sha256:243561d0af30e17aafb976989f1189ab670d79585b2829f5fdd6f40157f49438"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5UCBUQ277IRIJIJQWQEH7KIRB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Biao Luo, Guo-Tao Li, Mei-Jiang Gui, Qi-Chao Zhang, Shi-Qi Liu, Shuang-Yi Wang, Xiao-Hu Zhou, Xiao-Liang Xie, Xiao-Yin Liu, Zeng-Guang Hou","submitted_at":"2023-09-16T08:39:28Z","abstract_excerpt":"Model-based reinforcement learning (RL), which learns an environment model from the offline dataset and generates more out-of-distribution model data, has become an effective approach to the problem of distribution shift in offline RL. Due to the gap between the learned and actual environment, conservatism should be incorporated into the algorithm to balance accurate offline data and imprecise model data. The conservatism of current algorithms mostly relies on model uncertainty estimation. However, uncertainty estimation is unreliable and leads to poor performance in certain scenarios, and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08925","kind":"arxiv","version":4},"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/2309.08925/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":"2026-07-05T11:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+iUn389QiSy5JCp7vi5b/iuGPGr8qOZa+dnhznCoJJ6qM+R0MlG1oLZeT6YgHnZI9ypNlu1mhxX4BHsWeYkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:18:23.509836Z"},"content_sha256":"3bd0b8e2ba1aa2a4c42fdf75da54e083eb877ce40e89e21ce4892ecc6a75af0e","schema_version":"1.0","event_id":"sha256:3bd0b8e2ba1aa2a4c42fdf75da54e083eb877ce40e89e21ce4892ecc6a75af0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UCBUQ277IRIJIJQWQEH7KIRB5/bundle.json","state_url":"https://pith.science/pith/5UCBUQ277IRIJIJQWQEH7KIRB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UCBUQ277IRIJIJQWQEH7KIRB5/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":"2026-08-22T03:18:23Z","links":{"resolver":"https://pith.science/pith/5UCBUQ277IRIJIJQWQEH7KIRB5","bundle":"https://pith.science/pith/5UCBUQ277IRIJIJQWQEH7KIRB5/bundle.json","state":"https://pith.science/pith/5UCBUQ277IRIJIJQWQEH7KIRB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UCBUQ277IRIJIJQWQEH7KIRB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5UCBUQ277IRIJIJQWQEH7KIRB5","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":"705a235ca5b49748bd3896f34e5b5940c80ec8b581bcc2bf0d8f074a7c99d4b5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-16T08:39:28Z","title_canon_sha256":"6aa9fb3d51f29352ead2740bc4b883280539653599cf46d8c56316c50298957c"},"schema_version":"1.0","source":{"id":"2309.08925","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08925","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08925v4","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08925","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"5UCBUQ277IRI","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"5UCBUQ277IRIJIJQ","created_at":"2026-07-05T11:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"5UCBUQ27","created_at":"2026-07-05T11:18:10Z"}],"graph_snapshots":[{"event_id":"sha256:3bd0b8e2ba1aa2a4c42fdf75da54e083eb877ce40e89e21ce4892ecc6a75af0e","target":"graph","created_at":"2026-07-05T11:18:10Z","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/2309.08925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (RL), which learns an environment model from the offline dataset and generates more out-of-distribution model data, has become an effective approach to the problem of distribution shift in offline RL. Due to the gap between the learned and actual environment, conservatism should be incorporated into the algorithm to balance accurate offline data and imprecise model data. The conservatism of current algorithms mostly relies on model uncertainty estimation. However, uncertainty estimation is unreliable and leads to poor performance in certain scenarios, and the","authors_text":"Biao Luo, Guo-Tao Li, Mei-Jiang Gui, Qi-Chao Zhang, Shi-Qi Liu, Shuang-Yi Wang, Xiao-Hu Zhou, Xiao-Liang Xie, Xiao-Yin Liu, Zeng-Guang Hou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-16T08:39:28Z","title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08925","kind":"arxiv","version":4},"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":"sha256:243561d0af30e17aafb976989f1189ab670d79585b2829f5fdd6f40157f49438","target":"record","created_at":"2026-07-05T11:18:10Z","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":"705a235ca5b49748bd3896f34e5b5940c80ec8b581bcc2bf0d8f074a7c99d4b5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-16T08:39:28Z","title_canon_sha256":"6aa9fb3d51f29352ead2740bc4b883280539653599cf46d8c56316c50298957c"},"schema_version":"1.0","source":{"id":"2309.08925","kind":"arxiv","version":4}},"canonical_sha256":"ed041a435ffa2284a130b4087fa9110f58fbb500e1a608459f722748c2bb8f4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed041a435ffa2284a130b4087fa9110f58fbb500e1a608459f722748c2bb8f4d","first_computed_at":"2026-07-05T11:18:10.574394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:10.574394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysSigbtMvdHIPKrNyZoQum3E1j2iHiC4whEftc8Y+CCzaIFg6zMXws3TbIKtGpF302Gu1VrZnG7eOOSTFB7/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:10.574822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08925","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243561d0af30e17aafb976989f1189ab670d79585b2829f5fdd6f40157f49438","sha256:3bd0b8e2ba1aa2a4c42fdf75da54e083eb877ce40e89e21ce4892ecc6a75af0e"],"state_sha256":"ca747dd895547b6162565a37a841ee01192b98a0fff6702959931fef5556d148"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaU8OvC/xBrxpGGLkE8nV4fbGVg2dxj1OCF0dMAYoDuqzXRXpsDUN1Byxb1/45gTXtkmVGc0WH2sOwXTFe2OBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:18:23.515643Z","bundle_sha256":"bfa7d014094b4b5f01c22d22090c49598e6cf3af9bde5582a61e819fe76ded5d"}}