{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IFFSEQZUSTFULSSIAMWLSGKJBP","short_pith_number":"pith:IFFSEQZU","schema_version":"1.0","canonical_sha256":"414b22433494cb45ca48032cb919490be04b9f93b48b41a392013a7b210b719d","source":{"kind":"arxiv","id":"2505.06482","version":2},"attestation_state":"computed","paper":{"title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiajian Li, Minting Pan, Xiaokang Yang, Yitao Zheng, Yunbo Wang","submitted_at":"2025-05-10T00:54:12Z","abstract_excerpt":"Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation due to the lack of environmental interaction. We present Video-Enhanced Offline RL (VeoRL), a model-based method that constructs an interactive world model from diverse, unlabeled video data readily available online. Leveraging model-based behavior guidance, our approach transfers commonsense knowledge of control policy and physical dynamics from natural vi"},"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":"2505.06482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:54:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"acf2a6aa9b1096b09f40c0b40c0c283840633e67119f7d8a08d3249c6412c6e5","abstract_canon_sha256":"2ca906500d877225aa8463791ea20c3748e58c92a5149fd7f6cdf3c27c5ad9f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:50.876116Z","signature_b64":"F/XoveBbHqnvSHHetlKJPCk6qccUQw8VBsAMVmJ/wuxABiHAxWfsDxsxkPzxb/11A72sIcgvpSPn5V1AaN2SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414b22433494cb45ca48032cb919490be04b9f93b48b41a392013a7b210b719d","last_reissued_at":"2026-07-05T11:04:50.875615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:50.875615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiajian Li, Minting Pan, Xiaokang Yang, Yitao Zheng, Yunbo Wang","submitted_at":"2025-05-10T00:54:12Z","abstract_excerpt":"Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation due to the lack of environmental interaction. We present Video-Enhanced Offline RL (VeoRL), a model-based method that constructs an interactive world model from diverse, unlabeled video data readily available online. Leveraging model-based behavior guidance, our approach transfers commonsense knowledge of control policy and physical dynamics from natural vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06482","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/2505.06482/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":"2505.06482","created_at":"2026-07-05T11:04:50.875680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06482v2","created_at":"2026-07-05T11:04:50.875680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06482","created_at":"2026-07-05T11:04:50.875680+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFFSEQZUSTFU","created_at":"2026-07-05T11:04:50.875680+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFFSEQZUSTFULSSI","created_at":"2026-07-05T11:04:50.875680+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFFSEQZU","created_at":"2026-07-05T11:04:50.875680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP","json":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP.json","graph_json":"https://pith.science/api/pith-number/IFFSEQZUSTFULSSIAMWLSGKJBP/graph.json","events_json":"https://pith.science/api/pith-number/IFFSEQZUSTFULSSIAMWLSGKJBP/events.json","paper":"https://pith.science/paper/IFFSEQZU"},"agent_actions":{"view_html":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP","download_json":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP.json","view_paper":"https://pith.science/paper/IFFSEQZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06482&json=true","fetch_graph":"https://pith.science/api/pith-number/IFFSEQZUSTFULSSIAMWLSGKJBP/graph.json","fetch_events":"https://pith.science/api/pith-number/IFFSEQZUSTFULSSIAMWLSGKJBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP/action/storage_attestation","attest_author":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP/action/author_attestation","sign_citation":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP/action/citation_signature","submit_replication":"https://pith.science/pith/IFFSEQZUSTFULSSIAMWLSGKJBP/action/replication_record"}},"created_at":"2026-07-05T11:04:50.875680+00:00","updated_at":"2026-07-05T11:04:50.875680+00:00"}