{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PQLQNIFDS4NYRORF5TEC2CFGU7","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":"5494fddd299e7d7dafca8953ceff7a93582f1f629e368ed8c2dd5fe77d7c1bd5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T15:46:11Z","title_canon_sha256":"3d2c2eaa326fa6c1e94fa01badd512b6b74ecc9f3ebd7dfff721c0a34820f45f"},"schema_version":"1.0","source":{"id":"2607.11720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11720","created_at":"2026-07-14T02:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11720v1","created_at":"2026-07-14T02:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11720","created_at":"2026-07-14T02:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"PQLQNIFDS4NY","created_at":"2026-07-14T02:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"PQLQNIFDS4NYRORF","created_at":"2026-07-14T02:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"PQLQNIFD","created_at":"2026-07-14T02:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:e57c331789078c2213ac1c2ad337f6da283c38273eb5e2a25d3289b425bac5c9","target":"graph","created_at":"2026-07-14T02:22:20Z","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/2607.11720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where interaction is costly or potentially hazardous. Standard O2O-RL pipelines train multiple candidate policies offline, evaluate them using off-policy or online evaluation, and then deploy and fine-tune the policy with the highest estimated value. However, as in offline pretraining, fine-tuning performance i","authors_text":"Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T15:46:11Z","title":"Active Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11720","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:b2e09102c542828457f4647248321e37b3e822cde5102ebd7603a43388a2c6a3","target":"record","created_at":"2026-07-14T02:22:20Z","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":"5494fddd299e7d7dafca8953ceff7a93582f1f629e368ed8c2dd5fe77d7c1bd5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T15:46:11Z","title_canon_sha256":"3d2c2eaa326fa6c1e94fa01badd512b6b74ecc9f3ebd7dfff721c0a34820f45f"},"schema_version":"1.0","source":{"id":"2607.11720","kind":"arxiv","version":1}},"canonical_sha256":"7c1706a0a3971b88ba25ecc82d08a6a7e8822aba362735cb947a7a5107de48ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c1706a0a3971b88ba25ecc82d08a6a7e8822aba362735cb947a7a5107de48ff","first_computed_at":"2026-07-14T02:22:20.718258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T02:22:20.718258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DbeLVQHvfpsQMG8NLRr52m8DfxCMRDDJOetJawwCXCGp1xP2H3x49bG9x8gVJMgs3cNZORoM4p/VKeE0+lC6Bg==","signature_status":"signed_v1","signed_at":"2026-07-14T02:22:20.719100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e09102c542828457f4647248321e37b3e822cde5102ebd7603a43388a2c6a3","sha256:e57c331789078c2213ac1c2ad337f6da283c38273eb5e2a25d3289b425bac5c9"],"state_sha256":"45af816256c054b5212f770bd5488f3e4ad96cc9b58ac79f70dea0624661c8d5"}