{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7OJY7CFBAC5NGDRMUJWKSZA76Y","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":"8470c4545c7779a273414de0d88e770b75cef15e4cb332cf5adf042ea5e410bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T09:52:22Z","title_canon_sha256":"9e3f23be41c01fd1658bdb011172c7b3d97264a3b9bf6c6857d1f4821fd7458f"},"schema_version":"1.0","source":{"id":"2412.18855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18855","created_at":"2026-07-05T09:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18855v1","created_at":"2026-07-05T09:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18855","created_at":"2026-07-05T09:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"7OJY7CFBAC5N","created_at":"2026-07-05T09:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"7OJY7CFBAC5NGDRM","created_at":"2026-07-05T09:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"7OJY7CFB","created_at":"2026-07-05T09:54:11Z"}],"graph_snapshots":[{"event_id":"sha256:887767985541e0898c05424123180ee35d0620efdfa0108fee88474c88d250b1","target":"graph","created_at":"2026-07-05T09:54:11Z","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/2412.18855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online (O2O) reinforcement learning (RL) provides an effective means of leveraging an offline pre-trained policy as initialization to improve performance rapidly with limited online interactions. Recent studies often design fine-tuning strategies for a specific offline RL method and cannot perform general O2O learning from any offline method. To deal with this problem, we disclose that there are evaluation and improvement mismatches between the offline dataset and the online environment, which hinders the direct application of pre-trained policies to online fine-tuning. In this pape","authors_text":"Ming-Kun Xie, Qin-Wen Luo, Sheng-Jun Huang, Ye-Wen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T09:52:22Z","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18855","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":"sha256:122cf34a03edfbed269af68eff9ea80437dff5355bfe941433f95b41c717a416","target":"record","created_at":"2026-07-05T09:54:11Z","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":"8470c4545c7779a273414de0d88e770b75cef15e4cb332cf5adf042ea5e410bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T09:52:22Z","title_canon_sha256":"9e3f23be41c01fd1658bdb011172c7b3d97264a3b9bf6c6857d1f4821fd7458f"},"schema_version":"1.0","source":{"id":"2412.18855","kind":"arxiv","version":1}},"canonical_sha256":"fb938f88a100bad30e2ca26ca9641ff62bae29d59f0685c5c7039c8bf66b128c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb938f88a100bad30e2ca26ca9641ff62bae29d59f0685c5c7039c8bf66b128c","first_computed_at":"2026-07-05T09:54:11.956612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:11.956612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ADvtgHGvj6Epw9ZR/cpoCQ+/MefR+nAXoh0+aL4362NAlZ0xzBV9SFkk8/dfBVJ2M0LmOdOrxZbJZI3n8zHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:11.957064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:122cf34a03edfbed269af68eff9ea80437dff5355bfe941433f95b41c717a416","sha256:887767985541e0898c05424123180ee35d0620efdfa0108fee88474c88d250b1"],"state_sha256":"0fc1fb14a02254b91588eb3aa5fa12bb61d6e55e9ed87524305a7e257a009cab"}