{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IFFSEQZUSTFULSSIAMWLSGKJBP","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":"2ca906500d877225aa8463791ea20c3748e58c92a5149fd7f6cdf3c27c5ad9f4","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:54:12Z","title_canon_sha256":"acf2a6aa9b1096b09f40c0b40c0c283840633e67119f7d8a08d3249c6412c6e5"},"schema_version":"1.0","source":{"id":"2505.06482","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06482","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06482v2","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06482","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"IFFSEQZUSTFU","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"IFFSEQZUSTFULSSI","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"IFFSEQZU","created_at":"2026-07-05T11:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:78ed75ba20327e4eb13ed296f1da33d4beb112915d012d868ea6559220fa80da","target":"graph","created_at":"2026-07-05T11:04:50Z","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/2505.06482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiajian Li, Minting Pan, Xiaokang Yang, Yitao Zheng, Yunbo Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:54:12Z","title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06482","kind":"arxiv","version":2},"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":"sha256:2784a6c8ea9baf8b76677730fdb59f3f6fbe513ae96102eaa517274fb25553ec","target":"record","created_at":"2026-07-05T11:04:50Z","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":"2ca906500d877225aa8463791ea20c3748e58c92a5149fd7f6cdf3c27c5ad9f4","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-10T00:54:12Z","title_canon_sha256":"acf2a6aa9b1096b09f40c0b40c0c283840633e67119f7d8a08d3249c6412c6e5"},"schema_version":"1.0","source":{"id":"2505.06482","kind":"arxiv","version":2}},"canonical_sha256":"414b22433494cb45ca48032cb919490be04b9f93b48b41a392013a7b210b719d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"414b22433494cb45ca48032cb919490be04b9f93b48b41a392013a7b210b719d","first_computed_at":"2026-07-05T11:04:50.875615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:50.875615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/XoveBbHqnvSHHetlKJPCk6qccUQw8VBsAMVmJ/wuxABiHAxWfsDxsxkPzxb/11A72sIcgvpSPn5V1AaN2SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:50.876116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06482","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2784a6c8ea9baf8b76677730fdb59f3f6fbe513ae96102eaa517274fb25553ec","sha256:78ed75ba20327e4eb13ed296f1da33d4beb112915d012d868ea6559220fa80da"],"state_sha256":"882797951ffbe306b2361701bc6b767e00efd432048da48e35fdc348ba4a135b"}