{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7HC6YYIRC7MO5CI2AR6PXGD3NL","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":"e12821390ae7821877ea02cb662ed70ee3519ac3a668248d36546b3e47a11a13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T14:08:36Z","title_canon_sha256":"5992da10e29846cd4d78dcc47e563405ada0051171d1738508f2bcde314ba159"},"schema_version":"1.0","source":{"id":"2506.19643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19643","created_at":"2026-07-05T11:26:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19643v1","created_at":"2026-07-05T11:26:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19643","created_at":"2026-07-05T11:26:36Z"},{"alias_kind":"pith_short_12","alias_value":"7HC6YYIRC7MO","created_at":"2026-07-05T11:26:36Z"},{"alias_kind":"pith_short_16","alias_value":"7HC6YYIRC7MO5CI2","created_at":"2026-07-05T11:26:36Z"},{"alias_kind":"pith_short_8","alias_value":"7HC6YYIR","created_at":"2026-07-05T11:26:36Z"}],"graph_snapshots":[{"event_id":"sha256:c50619fa744a35226b8120d2d4dd16ed1e5599d3be214dd63ab0bed747915124","target":"graph","created_at":"2026-07-05T11:26:36Z","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/2506.19643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) recently gains growing interests from RL researchers. However, the performance of offline RL suffers from the out-of-distribution problem, which can be corrected by feedback in online RL. Previous offline RL research focuses on restricting the offline algorithm in in-distribution even in-sample action sampling. In contrast, fewer work pays attention to the influence of the batch data. In this paper, we first build a bridge over the batch data and the performance of offline RL algorithms theoretically, from the perspective of model-based offline RL optimizati","authors_text":"Hongchang Zhang, Jianzhun Shao, Shuncheng He, Xiangyang Ji, Yuhang Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T14:08:36Z","title":"Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19643","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":"sha256:17e6d0b1853263c23fe2b434fb0e7c16a45edc81800f65ba513c8d7f5e035b6f","target":"record","created_at":"2026-07-05T11:26:36Z","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":"e12821390ae7821877ea02cb662ed70ee3519ac3a668248d36546b3e47a11a13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T14:08:36Z","title_canon_sha256":"5992da10e29846cd4d78dcc47e563405ada0051171d1738508f2bcde314ba159"},"schema_version":"1.0","source":{"id":"2506.19643","kind":"arxiv","version":1}},"canonical_sha256":"f9c5ec611117d8ee891a047cfb987b6ad6a085a3267e69ffab9b06b63faff905","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9c5ec611117d8ee891a047cfb987b6ad6a085a3267e69ffab9b06b63faff905","first_computed_at":"2026-07-05T11:26:36.065807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:36.065807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ci2yoji7GX0cNMMb+YnJl8jUp0XJrLgGKr1EuxhgiwFqTLIlAN/elQacFFoxiCMQKhmDY9ON/EyTVb3JI59sBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:36.066280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17e6d0b1853263c23fe2b434fb0e7c16a45edc81800f65ba513c8d7f5e035b6f","sha256:c50619fa744a35226b8120d2d4dd16ed1e5599d3be214dd63ab0bed747915124"],"state_sha256":"a946e32aaa250cd4ec54e006a65d81c6a1ff1a6bfecca56ae57fadaa9d4aa2da"}