{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QS2BMX6TBGALRVFNA3JXXXTH75","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":"13ad93c2b561159fe400e3741a44a3abf916af42741064af0af247b91fbc2daa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T15:16:38Z","title_canon_sha256":"25e95ceb1dda6e1fb9be0e6efe6591963aeeb517235273ef730bab27d6d71cc5"},"schema_version":"1.0","source":{"id":"2406.09486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09486","created_at":"2026-07-05T08:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09486v1","created_at":"2026-07-05T08:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09486","created_at":"2026-07-05T08:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"QS2BMX6TBGAL","created_at":"2026-07-05T08:31:54Z"},{"alias_kind":"pith_short_16","alias_value":"QS2BMX6TBGALRVFN","created_at":"2026-07-05T08:31:54Z"},{"alias_kind":"pith_short_8","alias_value":"QS2BMX6T","created_at":"2026-07-05T08:31:54Z"}],"graph_snapshots":[{"event_id":"sha256:ccb3ebf09a8ed33dc77e1be035dfd99931a31a3d16ed02ec56e5b3d09a51a4b4","target":"graph","created_at":"2026-07-05T08:31:54Z","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/2406.09486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the distribution shift issue in offline RL, existing model-based methods heavily rely on the uncertainty of learned dynamics. However, the model uncertainty estimation becomes significantly biased when observations contain complex distractors with non-trivial dynamics. To address this challenge, we propose a new approach - \\emph{Separated Model-based Offline Polic","authors_text":"De-Chuan Zhan, Le Gan, ShengHua Wan, Shuai Feng, Ziyuan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T15:16:38Z","title":"SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09486","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":"sha256:5f22782a693e2167281555a93cae26d88f521856733e22d38407f70fc309133c","target":"record","created_at":"2026-07-05T08:31:54Z","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":"13ad93c2b561159fe400e3741a44a3abf916af42741064af0af247b91fbc2daa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T15:16:38Z","title_canon_sha256":"25e95ceb1dda6e1fb9be0e6efe6591963aeeb517235273ef730bab27d6d71cc5"},"schema_version":"1.0","source":{"id":"2406.09486","kind":"arxiv","version":1}},"canonical_sha256":"84b4165fd30980b8d4ad06d37bde67ff71b08cd03ec0672c36da443403c62ee6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84b4165fd30980b8d4ad06d37bde67ff71b08cd03ec0672c36da443403c62ee6","first_computed_at":"2026-07-05T08:31:54.847663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:54.847663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vrA3yMqVXMOZS9rVmCEyKD7LimTdvBwlkjc33oZUx/3FK4enMbpH6CgwfSZ9lRM0p8Hg87rvm/Jh0Y0NOX06DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:54.848070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f22782a693e2167281555a93cae26d88f521856733e22d38407f70fc309133c","sha256:ccb3ebf09a8ed33dc77e1be035dfd99931a31a3d16ed02ec56e5b3d09a51a4b4"],"state_sha256":"ad3821cf1d9a1e34629eb523be3030200e544b9d2dca137e9e25d6fc8e4b3a60"}