{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZGHOB3V2OA4VPGBG7OKB6GWNDA","short_pith_number":"pith:ZGHOB3V2","canonical_record":{"source":{"id":"2407.12448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T09:56:51Z","cross_cats_sorted":[],"title_canon_sha256":"13f4e2cab4f44f7b39f66765e95f7ea846d39ad2691b9b43857dc59d51749170","abstract_canon_sha256":"b2f18d47806eeb923871fa0f7f2fc78292ab76752b42ffabb533a7386cc27090"},"schema_version":"1.0"},"canonical_sha256":"c98ee0eeba7039579826fb941f1acd180be7a9b13fb918edcc24ba992893acd0","source":{"kind":"arxiv","id":"2407.12448","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12448","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12448v2","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12448","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZGHOB3V2OA4V","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZGHOB3V2OA4VPGBG","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZGHOB3V2","created_at":"2026-07-05T09:02:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZGHOB3V2OA4VPGBG7OKB6GWNDA","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T09:56:51Z","cross_cats_sorted":[],"title_canon_sha256":"13f4e2cab4f44f7b39f66765e95f7ea846d39ad2691b9b43857dc59d51749170","abstract_canon_sha256":"b2f18d47806eeb923871fa0f7f2fc78292ab76752b42ffabb533a7386cc27090"},"schema_version":"1.0"},"canonical_sha256":"c98ee0eeba7039579826fb941f1acd180be7a9b13fb918edcc24ba992893acd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:41.510547Z","signature_b64":"n8rNniv5gaxvIfCtTbw68Aub08xsSehAPNchr1ouTgHxZgDTjph2SVIvX6MZtHjVpOEkLmZbNSMCGoP9kRQqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98ee0eeba7039579826fb941f1acd180be7a9b13fb918edcc24ba992893acd0","last_reissued_at":"2026-07-05T09:02:41.509987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:41.509987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12448","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBWNN/9H3iU57J3TaGEGm5kYCUHAYMxsGtmWWfYpPyeUpdlHkSJ4J3/QbP1T7PBbRMCuitjRQ0fBMzp8QJRwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:49:48.763694Z"},"content_sha256":"b58ee033e50494555429c67430af2a8a3496b625ff858b1126aac297af75cfe8","schema_version":"1.0","event_id":"sha256:b58ee033e50494555429c67430af2a8a3496b625ff858b1126aac297af75cfe8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZGHOB3V2OA4VPGBG7OKB6GWNDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruifeng Chen, Shengyi Jiang, Tian-Shuo Liu, Xinwei Chen, Xu-Hui Liu, Yang Yu, Zhilong Zhang","submitted_at":"2024-07-17T09:56:51Z","abstract_excerpt":"Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, \\textbf{E}nergy-guided \\textbf{DI}ffusion \\textbf{S}ampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12448","kind":"arxiv","version":2},"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/2407.12448/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":"2026-07-05T09:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJipQ9r1btb1QqjRPJo8uVjNl7mXnNb5aQEelUZoVP6ZEZzz6BT2pKrDvnQiMmyKiToSTbZmcDW02HXj1OIICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:49:48.764507Z"},"content_sha256":"6be26f5a59f8d76512954611204451cfc5dd9e1acff433d8a7738f09507cf380","schema_version":"1.0","event_id":"sha256:6be26f5a59f8d76512954611204451cfc5dd9e1acff433d8a7738f09507cf380"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA/bundle.json","state_url":"https://pith.science/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA/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":"2026-08-03T16:49:48Z","links":{"resolver":"https://pith.science/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA","bundle":"https://pith.science/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA/bundle.json","state":"https://pith.science/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGHOB3V2OA4VPGBG7OKB6GWNDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZGHOB3V2OA4VPGBG7OKB6GWNDA","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":"b2f18d47806eeb923871fa0f7f2fc78292ab76752b42ffabb533a7386cc27090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T09:56:51Z","title_canon_sha256":"13f4e2cab4f44f7b39f66765e95f7ea846d39ad2691b9b43857dc59d51749170"},"schema_version":"1.0","source":{"id":"2407.12448","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12448","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12448v2","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12448","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZGHOB3V2OA4V","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZGHOB3V2OA4VPGBG","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZGHOB3V2","created_at":"2026-07-05T09:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:6be26f5a59f8d76512954611204451cfc5dd9e1acff433d8a7738f09507cf380","target":"graph","created_at":"2026-07-05T09:02:41Z","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/2407.12448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, \\textbf{E}nergy-guided \\textbf{DI}ffusion \\textbf{S}ampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions t","authors_text":"Ruifeng Chen, Shengyi Jiang, Tian-Shuo Liu, Xinwei Chen, Xu-Hui Liu, Yang Yu, Zhilong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T09:56:51Z","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12448","kind":"arxiv","version":2},"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:b58ee033e50494555429c67430af2a8a3496b625ff858b1126aac297af75cfe8","target":"record","created_at":"2026-07-05T09:02:41Z","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":"b2f18d47806eeb923871fa0f7f2fc78292ab76752b42ffabb533a7386cc27090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T09:56:51Z","title_canon_sha256":"13f4e2cab4f44f7b39f66765e95f7ea846d39ad2691b9b43857dc59d51749170"},"schema_version":"1.0","source":{"id":"2407.12448","kind":"arxiv","version":2}},"canonical_sha256":"c98ee0eeba7039579826fb941f1acd180be7a9b13fb918edcc24ba992893acd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c98ee0eeba7039579826fb941f1acd180be7a9b13fb918edcc24ba992893acd0","first_computed_at":"2026-07-05T09:02:41.509987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:41.509987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n8rNniv5gaxvIfCtTbw68Aub08xsSehAPNchr1ouTgHxZgDTjph2SVIvX6MZtHjVpOEkLmZbNSMCGoP9kRQqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:41.510547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12448","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b58ee033e50494555429c67430af2a8a3496b625ff858b1126aac297af75cfe8","sha256:6be26f5a59f8d76512954611204451cfc5dd9e1acff433d8a7738f09507cf380"],"state_sha256":"7725fc5dd71d6e188277d7399d56d79b2000992ef2c6cc0c591964e6239687c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQ3Ae28smjdVxFNI6PwOCNbnaVFdmdQCaG9VWfoxCvwn3SO6SP7poJ5Q3kaEGipBZ2QHq5MIBU08kf/67AluCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:49:48.770224Z","bundle_sha256":"b36b027fdcc8d0a7ee6f015dba7a6d6ecf7795d778398a756c3a825ef9b1270a"}}