{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IPJ476YKFGQHHFV7OGJLO2EEFD","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":"78ee863c48c59553956e997e28110ecad4abf307889217845e10c23ddbbdf694","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:08:42Z","title_canon_sha256":"87d4aad112fb46cc50be7b1139506349baba538d4e0375c1b87a8ce6c36553fd"},"schema_version":"1.0","source":{"id":"2605.30776","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30776","created_at":"2026-06-01T01:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30776v1","created_at":"2026-06-01T01:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30776","created_at":"2026-06-01T01:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"IPJ476YKFGQH","created_at":"2026-06-01T01:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"IPJ476YKFGQHHFV7","created_at":"2026-06-01T01:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"IPJ476YK","created_at":"2026-06-01T01:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:e04da1e1801ee895dee4965e27ee1a813fc68b899ce9918bb06a727b9c7f5b3f","target":"graph","created_at":"2026-06-01T01:03:15Z","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/2605.30776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to shifts between offline and online distributions. Existing work aims to mitigate the harm of this shift by finetuning the policy on trajectory data sampled from a diffusion model. Inspired by this line of work, we propose DUAL: an efficient \\textbf{D}iffusion \\textbf{U}ncertainty-\\textbf{A}ware framework for offline-to-online reinforcement \\textbf{L}earning. DUAL utilizes the prior knowledge of the diffusion model to","authors_text":"Anqi Liu, Eric Nalisnick, Ha Manh Bui, Metod Jazbec","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:08:42Z","title":"Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30776","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:c8930d76a68a73b932425d33b47d81d5b0c404e3d5c01322dfbdf94b78eb1c1d","target":"record","created_at":"2026-06-01T01:03:15Z","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":"78ee863c48c59553956e997e28110ecad4abf307889217845e10c23ddbbdf694","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:08:42Z","title_canon_sha256":"87d4aad112fb46cc50be7b1139506349baba538d4e0375c1b87a8ce6c36553fd"},"schema_version":"1.0","source":{"id":"2605.30776","kind":"arxiv","version":1}},"canonical_sha256":"43d3cffb0a29a07396bf7192b7688428f66df7230c3e3629f885d046c359e87a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43d3cffb0a29a07396bf7192b7688428f66df7230c3e3629f885d046c359e87a","first_computed_at":"2026-06-01T01:03:15.948736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:15.948736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"epcymgZXl37Sl+kHNy/lrSwitSR6NojP4k2zju384TP1dFgVRDDfqQ/GT6zxPxRPON791tcpBfpPNRB7CEosAg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:15.949432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30776","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8930d76a68a73b932425d33b47d81d5b0c404e3d5c01322dfbdf94b78eb1c1d","sha256:e04da1e1801ee895dee4965e27ee1a813fc68b899ce9918bb06a727b9c7f5b3f"],"state_sha256":"b7ff8ecba2be8e49dae75eddfa5193cd26cb23382b2dd85ead339fa01f1ff90a"}