{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IPJ476YKFGQHHFV7OGJLO2EEFD","short_pith_number":"pith:IPJ476YK","schema_version":"1.0","canonical_sha256":"43d3cffb0a29a07396bf7192b7688428f66df7230c3e3629f885d046c359e87a","source":{"kind":"arxiv","id":"2605.30776","version":1},"attestation_state":"computed","paper":{"title":"Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Eric Nalisnick, Ha Manh Bui, Metod Jazbec","submitted_at":"2026-05-29T03:08:42Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.30776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:08:42Z","cross_cats_sorted":[],"title_canon_sha256":"87d4aad112fb46cc50be7b1139506349baba538d4e0375c1b87a8ce6c36553fd","abstract_canon_sha256":"78ee863c48c59553956e997e28110ecad4abf307889217845e10c23ddbbdf694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:15.949432Z","signature_b64":"epcymgZXl37Sl+kHNy/lrSwitSR6NojP4k2zju384TP1dFgVRDDfqQ/GT6zxPxRPON791tcpBfpPNRB7CEosAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43d3cffb0a29a07396bf7192b7688428f66df7230c3e3629f885d046c359e87a","last_reissued_at":"2026-06-01T01:03:15.948736Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:15.948736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Eric Nalisnick, Ha Manh Bui, Metod Jazbec","submitted_at":"2026-05-29T03:08:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30776","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.30776/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.30776","created_at":"2026-06-01T01:03:15.948851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30776v1","created_at":"2026-06-01T01:03:15.948851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30776","created_at":"2026-06-01T01:03:15.948851+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPJ476YKFGQH","created_at":"2026-06-01T01:03:15.948851+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPJ476YKFGQHHFV7","created_at":"2026-06-01T01:03:15.948851+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPJ476YK","created_at":"2026-06-01T01:03:15.948851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD","json":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD.json","graph_json":"https://pith.science/api/pith-number/IPJ476YKFGQHHFV7OGJLO2EEFD/graph.json","events_json":"https://pith.science/api/pith-number/IPJ476YKFGQHHFV7OGJLO2EEFD/events.json","paper":"https://pith.science/paper/IPJ476YK"},"agent_actions":{"view_html":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD","download_json":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD.json","view_paper":"https://pith.science/paper/IPJ476YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30776&json=true","fetch_graph":"https://pith.science/api/pith-number/IPJ476YKFGQHHFV7OGJLO2EEFD/graph.json","fetch_events":"https://pith.science/api/pith-number/IPJ476YKFGQHHFV7OGJLO2EEFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD/action/storage_attestation","attest_author":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD/action/author_attestation","sign_citation":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD/action/citation_signature","submit_replication":"https://pith.science/pith/IPJ476YKFGQHHFV7OGJLO2EEFD/action/replication_record"}},"created_at":"2026-06-01T01:03:15.948851+00:00","updated_at":"2026-06-01T01:03:15.948851+00:00"}