{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7MPI5L5GFPRI4BSRQMXML7LDSW","short_pith_number":"pith:7MPI5L5G","canonical_record":{"source":{"id":"2306.05412","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9591eca51ad26dda78a72e9565766dfef9de7db13e41adfdf9d16e5b35fad2c6","abstract_canon_sha256":"97cbb688b2cf3796efa6f5cdc319ddcd016660c699430aabb720aae0a9332919"},"schema_version":"1.0"},"canonical_sha256":"fb1e8eafa62be28e0651832ec5fd6395a02533e6bab34857a84c9c62b4413ef3","source":{"kind":"arxiv","id":"2306.05412","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05412","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05412v4","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05412","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"pith_short_12","alias_value":"7MPI5L5GFPRI","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"pith_short_16","alias_value":"7MPI5L5GFPRI4BSR","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"pith_short_8","alias_value":"7MPI5L5G","created_at":"2026-07-05T09:58:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7MPI5L5GFPRI4BSRQMXML7LDSW","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05412","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9591eca51ad26dda78a72e9565766dfef9de7db13e41adfdf9d16e5b35fad2c6","abstract_canon_sha256":"97cbb688b2cf3796efa6f5cdc319ddcd016660c699430aabb720aae0a9332919"},"schema_version":"1.0"},"canonical_sha256":"fb1e8eafa62be28e0651832ec5fd6395a02533e6bab34857a84c9c62b4413ef3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:16.100139Z","signature_b64":"PcxGVC5m6ReE4iITi+8KSWRw4LKy6IxKIxWSHjwIlBhpsZf1tZMpQTEAZ3Q1BliinQKGOCEDpGDoDJPgZSsuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb1e8eafa62be28e0651832ec5fd6395a02533e6bab34857a84c9c62b4413ef3","last_reissued_at":"2026-07-05T09:58:16.099733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:16.099733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05412","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqMdrFgsaAyrPzCQLZGQKesfiLM4zmxfJ//oyhjfwN+w1Wj8sJMzNwWEmPV0a963iwl1z5gwbTB9LGcxvlepBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:48:55.781100Z"},"content_sha256":"8a1150e83bcc70457a4e19553ed05c02baabb096fd73a139d40a0522ad4640da","schema_version":"1.0","event_id":"sha256:8a1150e83bcc70457a4e19553ed05c02baabb096fd73a139d40a0522ad4640da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7MPI5L5GFPRI4BSRQMXML7LDSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupled Prioritized Resampling for Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingyi Kang, Gao Huang, Qisen Yang, Shiji Song, Shuicheng Yan, Xiao Ma, Yang Yue","submitted_at":"2023-06-08T17:56:46Z","abstract_excerpt":"Offline reinforcement learning (RL) is challenged by the distributional shift problem. To address this problem, existing works mainly focus on designing sophisticated policy constraints between the learned policy and the behavior policy. However, these constraints are applied equally to well-performing and inferior actions through uniform sampling, which might negatively affect the learned policy. To alleviate this issue, we propose Offline Prioritized Experience Replay (OPER), featuring a class of priority functions designed to prioritize highly-rewarding transitions, making them more frequen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05412","kind":"arxiv","version":4},"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/2306.05412/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":"2026-07-05T09:58:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVq3Z9W1qHcSUBDagAHouwJH/EIR5vAoTb7Ea5lmrIwn2XwnpWM96bdrBQ1DUspgI6Mc1VTAqrjtewOd2uTsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:48:55.781499Z"},"content_sha256":"5fe44856819b0d87f2bae2a5bf0d151fc7a05b341e0542775aff91ab2ea4a14f","schema_version":"1.0","event_id":"sha256:5fe44856819b0d87f2bae2a5bf0d151fc7a05b341e0542775aff91ab2ea4a14f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MPI5L5GFPRI4BSRQMXML7LDSW/bundle.json","state_url":"https://pith.science/pith/7MPI5L5GFPRI4BSRQMXML7LDSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MPI5L5GFPRI4BSRQMXML7LDSW/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":"2026-07-09T02:48:55Z","links":{"resolver":"https://pith.science/pith/7MPI5L5GFPRI4BSRQMXML7LDSW","bundle":"https://pith.science/pith/7MPI5L5GFPRI4BSRQMXML7LDSW/bundle.json","state":"https://pith.science/pith/7MPI5L5GFPRI4BSRQMXML7LDSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MPI5L5GFPRI4BSRQMXML7LDSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7MPI5L5GFPRI4BSRQMXML7LDSW","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":"97cbb688b2cf3796efa6f5cdc319ddcd016660c699430aabb720aae0a9332919","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:56:46Z","title_canon_sha256":"9591eca51ad26dda78a72e9565766dfef9de7db13e41adfdf9d16e5b35fad2c6"},"schema_version":"1.0","source":{"id":"2306.05412","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05412","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05412v4","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05412","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"pith_short_12","alias_value":"7MPI5L5GFPRI","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"pith_short_16","alias_value":"7MPI5L5GFPRI4BSR","created_at":"2026-07-05T09:58:16Z"},{"alias_kind":"pith_short_8","alias_value":"7MPI5L5G","created_at":"2026-07-05T09:58:16Z"}],"graph_snapshots":[{"event_id":"sha256:5fe44856819b0d87f2bae2a5bf0d151fc7a05b341e0542775aff91ab2ea4a14f","target":"graph","created_at":"2026-07-05T09:58:16Z","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/2306.05412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is challenged by the distributional shift problem. To address this problem, existing works mainly focus on designing sophisticated policy constraints between the learned policy and the behavior policy. However, these constraints are applied equally to well-performing and inferior actions through uniform sampling, which might negatively affect the learned policy. To alleviate this issue, we propose Offline Prioritized Experience Replay (OPER), featuring a class of priority functions designed to prioritize highly-rewarding transitions, making them more frequen","authors_text":"Bingyi Kang, Gao Huang, Qisen Yang, Shiji Song, Shuicheng Yan, Xiao Ma, Yang Yue","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:56:46Z","title":"Decoupled Prioritized Resampling for Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05412","kind":"arxiv","version":4},"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":"sha256:8a1150e83bcc70457a4e19553ed05c02baabb096fd73a139d40a0522ad4640da","target":"record","created_at":"2026-07-05T09:58:16Z","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":"97cbb688b2cf3796efa6f5cdc319ddcd016660c699430aabb720aae0a9332919","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:56:46Z","title_canon_sha256":"9591eca51ad26dda78a72e9565766dfef9de7db13e41adfdf9d16e5b35fad2c6"},"schema_version":"1.0","source":{"id":"2306.05412","kind":"arxiv","version":4}},"canonical_sha256":"fb1e8eafa62be28e0651832ec5fd6395a02533e6bab34857a84c9c62b4413ef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb1e8eafa62be28e0651832ec5fd6395a02533e6bab34857a84c9c62b4413ef3","first_computed_at":"2026-07-05T09:58:16.099733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:16.099733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PcxGVC5m6ReE4iITi+8KSWRw4LKy6IxKIxWSHjwIlBhpsZf1tZMpQTEAZ3Q1BliinQKGOCEDpGDoDJPgZSsuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:16.100139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05412","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a1150e83bcc70457a4e19553ed05c02baabb096fd73a139d40a0522ad4640da","sha256:5fe44856819b0d87f2bae2a5bf0d151fc7a05b341e0542775aff91ab2ea4a14f"],"state_sha256":"e10a6d73b2c4b6e6b862c5dc542e65bfa0636ea8b00e3dbf9717b2caf8d36419"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Osc/lMnA19pYJlYxhBhXzN/u3mva9KWAnozJfCyEqj7un6dvKFMMbWiTwcDHq77ODS4ZaAeWrHSBJubrQtjsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:48:55.783586Z","bundle_sha256":"841b594a885e64898ff0fea8f14383ca929cfff043ba68b5263624060273fcb2"}}