{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZRJ25QH4RNIJKJQM3AFYBQYTZD","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":"394a0fe4031c28d8023a918801fe7a8a364d13fb26e68bb493ce2ae16d62c535","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T08:00:12Z","title_canon_sha256":"977242382b42b059e8b2af0ab16c2353675cd65e67f2de523d632cb37d76f483"},"schema_version":"1.0","source":{"id":"2507.08387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08387","created_at":"2026-07-05T11:35:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08387v1","created_at":"2026-07-05T11:35:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08387","created_at":"2026-07-05T11:35:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZRJ25QH4RNIJ","created_at":"2026-07-05T11:35:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZRJ25QH4RNIJKJQM","created_at":"2026-07-05T11:35:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZRJ25QH4","created_at":"2026-07-05T11:35:37Z"}],"graph_snapshots":[{"event_id":"sha256:43d1acd30fcfaf91f5b0a6c00266cdb30f9e802a8fbf219345f517054772654b","target":"graph","created_at":"2026-07-05T11:35:37Z","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/2507.08387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online reinforcement learning (RL) aims to integrate the complementary strengths of offline and online RL by pre-training an agent offline and subsequently fine-tuning it through online interactions. However, recent studies reveal that offline pre-trained agents often underperform during online fine-tuning due to inaccurate value estimation caused by distribution shift, with random initialization proving more effective in certain cases. In this work, we propose a novel method, Online Pre-Training for Offline-to-Online RL (OPT), explicitly designed to address the issue of inaccurate ","authors_text":"Deunsol Yoon, Geonhyeong Kim, Jeonghye Kim, Jongseong Chae, Kanghoon Lee, Sunghoon Hong, Whiyoung Jung, Woohyung Lim, Yongjae Shin, Youngchul Sung, Youngsoo Jang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T08:00:12Z","title":"Online Pre-Training for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08387","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:bb08780b33400d05f1d28ddf72ade9fd38cc63bb7c27a9dc55faa7d584455f50","target":"record","created_at":"2026-07-05T11:35:37Z","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":"394a0fe4031c28d8023a918801fe7a8a364d13fb26e68bb493ce2ae16d62c535","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T08:00:12Z","title_canon_sha256":"977242382b42b059e8b2af0ab16c2353675cd65e67f2de523d632cb37d76f483"},"schema_version":"1.0","source":{"id":"2507.08387","kind":"arxiv","version":1}},"canonical_sha256":"cc53aec0fc8b5095260cd80b80c313c8ca2af4118d69af242df06764da3573b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc53aec0fc8b5095260cd80b80c313c8ca2af4118d69af242df06764da3573b0","first_computed_at":"2026-07-05T11:35:37.200090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:37.200090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Np/SFXqSUsNsNtNbQODFdKDPw8b4x625ID0caXDR7I1GLzHe8EIhFd/6f9JwU1/1125TDtm0gBFUitxIgkYZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:37.200577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb08780b33400d05f1d28ddf72ade9fd38cc63bb7c27a9dc55faa7d584455f50","sha256:43d1acd30fcfaf91f5b0a6c00266cdb30f9e802a8fbf219345f517054772654b"],"state_sha256":"7d802cbfc9d303921e56136cc72ffe44d73cc80c566b3b22add0fd4259417a8a"}