{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KO7K2CO4FSVUKHERAAXSFHT4BM","short_pith_number":"pith:KO7K2CO4","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"},"canonical_sha256":"53bead09dc2cab451c91002f229e7c0b084bae1c94dfc74a2a5a530613439507","source":{"kind":"arxiv","id":"2508.06806","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06806","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06806v1","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06806","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"KO7K2CO4FSVU","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"KO7K2CO4FSVUKHER","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"KO7K2CO4","created_at":"2026-07-05T11:51:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KO7K2CO4FSVUKHERAAXSFHT4BM","target":"record","payload":{"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"},"canonical_sha256":"53bead09dc2cab451c91002f229e7c0b084bae1c94dfc74a2a5a530613439507","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"},"source_kind":"arxiv","source_id":"2508.06806","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lir+4A8Agx/43bffcQg0u4gTzpv1nBMjdM+od7aWFgQfcn+HyE/VSX33/5THJkkacL71jW1JwhNjdh9QDK46CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:54:55.351070Z"},"content_sha256":"7eb5f973dfb1a6b9ad233d469dc8d3a3a522698f8582f91dfe10adb13d762397","schema_version":"1.0","event_id":"sha256:7eb5f973dfb1a6b9ad233d469dc8d3a3a522698f8582f91dfe10adb13d762397"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KO7K2CO4FSVUKHERAAXSFHT4BM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UgMqmcqPVrKDDmMTXphnB0D6YqJea1cJ5zXqbO2/dUTp81u3GR4nOapQRisu3EIukBbhJss3XgEvZ6FLxcaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:54:55.351485Z"},"content_sha256":"62ddd2b6f5b0be17e6db0a26b8a82bea1484d18bcce435c26e4d84e7a475a36e","schema_version":"1.0","event_id":"sha256:62ddd2b6f5b0be17e6db0a26b8a82bea1484d18bcce435c26e4d84e7a475a36e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/bundle.json","state_url":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:54:55Z","links":{"resolver":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM","bundle":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/bundle.json","state":"https://pith.science/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KO7K2CO4FSVUKHERAAXSFHT4BM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KO7K2CO4FSVUKHERAAXSFHT4BM","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":"d783a83ff0c90b82e1811732446af6cc22b4b6430894f835c1cd4e81ebe6ee8e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T03:32:23Z","title_canon_sha256":"ffb4d1c0c0a3c9019f74bf982055cf391295f9decce991b458ec0a9c7d3c21a7"},"schema_version":"1.0","source":{"id":"2508.06806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06806","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06806v1","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06806","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"KO7K2CO4FSVU","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"KO7K2CO4FSVUKHER","created_at":"2026-07-05T11:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"KO7K2CO4","created_at":"2026-07-05T11:51:35Z"}],"graph_snapshots":[{"event_id":"sha256:62ddd2b6f5b0be17e6db0a26b8a82bea1484d18bcce435c26e4d84e7a475a36e","target":"graph","created_at":"2026-07-05T11:51:35Z","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/2508.06806/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) 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","authors_text":"Enze Zhang, Shuai Li, Tong Yu, Xiao Huang, Xu Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T03:32:23Z","title":"Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06806","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":"sha256:7eb5f973dfb1a6b9ad233d469dc8d3a3a522698f8582f91dfe10adb13d762397","target":"record","created_at":"2026-07-05T11:51:35Z","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":"d783a83ff0c90b82e1811732446af6cc22b4b6430894f835c1cd4e81ebe6ee8e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T03:32:23Z","title_canon_sha256":"ffb4d1c0c0a3c9019f74bf982055cf391295f9decce991b458ec0a9c7d3c21a7"},"schema_version":"1.0","source":{"id":"2508.06806","kind":"arxiv","version":1}},"canonical_sha256":"53bead09dc2cab451c91002f229e7c0b084bae1c94dfc74a2a5a530613439507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53bead09dc2cab451c91002f229e7c0b084bae1c94dfc74a2a5a530613439507","first_computed_at":"2026-07-05T11:51:35.720590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:35.720590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gtmzie6J8yK21wcPeom1t6KGR66bKs2AaEb9XeGRWFESZKbmld5RWhAH2cWenb0f+/cdUcRtbvbqM2dAO+H/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:35.721090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eb5f973dfb1a6b9ad233d469dc8d3a3a522698f8582f91dfe10adb13d762397","sha256:62ddd2b6f5b0be17e6db0a26b8a82bea1484d18bcce435c26e4d84e7a475a36e"],"state_sha256":"0cc659f0dcce3d9cb24f0f27b8cb5f2098c6dfb802a0f34b0ffd03329d62842b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j0vxIks6QrnpswYGcLDK0FYpniOYSJXqs5fbuY+8mE49urebfo1L3mFkImxyjtXhU0BZuUkFXbeAw08eQrz1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:54:55.354320Z","bundle_sha256":"7c694cf87055d34766b9ddaf8d27c49113441f71fe01f973721a0c60f7dfd313"}}