{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QS2BMX6TBGALRVFNA3JXXXTH75","short_pith_number":"pith:QS2BMX6T","schema_version":"1.0","canonical_sha256":"84b4165fd30980b8d4ad06d37bde67ff71b08cd03ec0672c36da443403c62ee6","source":{"kind":"arxiv","id":"2406.09486","version":1},"attestation_state":"computed","paper":{"title":"SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"De-Chuan Zhan, Le Gan, ShengHua Wan, Shuai Feng, Ziyuan Chen","submitted_at":"2024-06-13T15:16:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.09486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T15:16:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25e95ceb1dda6e1fb9be0e6efe6591963aeeb517235273ef730bab27d6d71cc5","abstract_canon_sha256":"13ad93c2b561159fe400e3741a44a3abf916af42741064af0af247b91fbc2daa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:54.848070Z","signature_b64":"vrA3yMqVXMOZS9rVmCEyKD7LimTdvBwlkjc33oZUx/3FK4enMbpH6CgwfSZ9lRM0p8Hg87rvm/Jh0Y0NOX06DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84b4165fd30980b8d4ad06d37bde67ff71b08cd03ec0672c36da443403c62ee6","last_reissued_at":"2026-07-05T08:31:54.847663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:54.847663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"De-Chuan Zhan, Le Gan, ShengHua Wan, Shuai Feng, Ziyuan Chen","submitted_at":"2024-06-13T15:16:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09486","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/2406.09486/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.09486","created_at":"2026-07-05T08:31:54.847719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09486v1","created_at":"2026-07-05T08:31:54.847719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09486","created_at":"2026-07-05T08:31:54.847719+00:00"},{"alias_kind":"pith_short_12","alias_value":"QS2BMX6TBGAL","created_at":"2026-07-05T08:31:54.847719+00:00"},{"alias_kind":"pith_short_16","alias_value":"QS2BMX6TBGALRVFN","created_at":"2026-07-05T08:31:54.847719+00:00"},{"alias_kind":"pith_short_8","alias_value":"QS2BMX6T","created_at":"2026-07-05T08:31:54.847719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12496","citing_title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75","json":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75.json","graph_json":"https://pith.science/api/pith-number/QS2BMX6TBGALRVFNA3JXXXTH75/graph.json","events_json":"https://pith.science/api/pith-number/QS2BMX6TBGALRVFNA3JXXXTH75/events.json","paper":"https://pith.science/paper/QS2BMX6T"},"agent_actions":{"view_html":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75","download_json":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75.json","view_paper":"https://pith.science/paper/QS2BMX6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09486&json=true","fetch_graph":"https://pith.science/api/pith-number/QS2BMX6TBGALRVFNA3JXXXTH75/graph.json","fetch_events":"https://pith.science/api/pith-number/QS2BMX6TBGALRVFNA3JXXXTH75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75/action/storage_attestation","attest_author":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75/action/author_attestation","sign_citation":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75/action/citation_signature","submit_replication":"https://pith.science/pith/QS2BMX6TBGALRVFNA3JXXXTH75/action/replication_record"}},"created_at":"2026-07-05T08:31:54.847719+00:00","updated_at":"2026-07-05T08:31:54.847719+00:00"}