{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KO7K2CO4FSVUKHERAAXSFHT4BM","short_pith_number":"pith:KO7K2CO4","schema_version":"1.0","canonical_sha256":"53bead09dc2cab451c91002f229e7c0b084bae1c94dfc74a2a5a530613439507","source":{"kind":"arxiv","id":"2508.06806","version":1},"attestation_state":"computed","paper":{"title":"Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Enze Zhang, Shuai Li, Tong Yu, Xiao Huang, Xu Liu","submitted_at":"2025-08-09T03:32:23Z","abstract_excerpt":"Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated data still exhibits a gap with the online data, limiting overall performance. To address this, we propose a new data augmentation approach, Classifier-Free Diffusion Generation (CFDG). Without introducing additional classifier training overhead, CFDG leverages classifier-free guidance diffusion to sig"},"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":"2508.06806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T03:32:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ffb4d1c0c0a3c9019f74bf982055cf391295f9decce991b458ec0a9c7d3c21a7","abstract_canon_sha256":"d783a83ff0c90b82e1811732446af6cc22b4b6430894f835c1cd4e81ebe6ee8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:35.721090Z","signature_b64":"gtmzie6J8yK21wcPeom1t6KGR66bKs2AaEb9XeGRWFESZKbmld5RWhAH2cWenb0f+/cdUcRtbvbqM2dAO+H/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53bead09dc2cab451c91002f229e7c0b084bae1c94dfc74a2a5a530613439507","last_reissued_at":"2026-07-05T11:51:35.720590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:35.720590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Enze Zhang, Shuai Li, Tong Yu, Xiao Huang, Xu Liu","submitted_at":"2025-08-09T03:32:23Z","abstract_excerpt":"Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated data still exhibits a gap with the online data, limiting overall performance. To address this, we propose a new data augmentation approach, Classifier-Free Diffusion Generation (CFDG). Without introducing additional classifier training overhead, CFDG leverages classifier-free guidance diffusion to sig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06806","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/2508.06806/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":"2508.06806","created_at":"2026-07-05T11:51:35.720651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06806v1","created_at":"2026-07-05T11:51:35.720651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06806","created_at":"2026-07-05T11:51:35.720651+00:00"},{"alias_kind":"pith_short_12","alias_value":"KO7K2CO4FSVU","created_at":"2026-07-05T11:51:35.720651+00:00"},{"alias_kind":"pith_short_16","alias_value":"KO7K2CO4FSVUKHER","created_at":"2026-07-05T11:51:35.720651+00:00"},{"alias_kind":"pith_short_8","alias_value":"KO7K2CO4","created_at":"2026-07-05T11:51:35.720651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13966","citing_title":"Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM","json":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM.json","graph_json":"https://pith.science/api/pith-number/KO7K2CO4FSVUKHERAAXSFHT4BM/graph.json","events_json":"https://pith.science/api/pith-number/KO7K2CO4FSVUKHERAAXSFHT4BM/events.json","paper":"https://pith.science/paper/KO7K2CO4"},"agent_actions":{"view_html":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM","download_json":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM.json","view_paper":"https://pith.science/paper/KO7K2CO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06806&json=true","fetch_graph":"https://pith.science/api/pith-number/KO7K2CO4FSVUKHERAAXSFHT4BM/graph.json","fetch_events":"https://pith.science/api/pith-number/KO7K2CO4FSVUKHERAAXSFHT4BM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/action/storage_attestation","attest_author":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/action/author_attestation","sign_citation":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/action/citation_signature","submit_replication":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/action/replication_record"}},"created_at":"2026-07-05T11:51:35.720651+00:00","updated_at":"2026-07-05T11:51:35.720651+00:00"}