{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WL4X7VKMHDJPVJUBIX4Y4QEBNY","short_pith_number":"pith:WL4X7VKM","canonical_record":{"source":{"id":"2404.10662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:39:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f96f779eab56d748d13fd1b0ef9cae7eb4b8106fcef7fa847f3e82a7649c2c8f","abstract_canon_sha256":"91134db7a5517bbb99c43801932015bcd837062e4573b36e116fab646864595f"},"schema_version":"1.0"},"canonical_sha256":"b2f97fd54c38d2faa68145f98e40816e32420fc0d58fc613c984de39a49a55a7","source":{"kind":"arxiv","id":"2404.10662","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10662","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10662v2","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10662","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"WL4X7VKMHDJP","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"WL4X7VKMHDJPVJUB","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"WL4X7VKM","created_at":"2026-07-05T08:09:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WL4X7VKMHDJPVJUBIX4Y4QEBNY","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:39:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f96f779eab56d748d13fd1b0ef9cae7eb4b8106fcef7fa847f3e82a7649c2c8f","abstract_canon_sha256":"91134db7a5517bbb99c43801932015bcd837062e4573b36e116fab646864595f"},"schema_version":"1.0"},"canonical_sha256":"b2f97fd54c38d2faa68145f98e40816e32420fc0d58fc613c984de39a49a55a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:30.574928Z","signature_b64":"rHpZQhAOw8Slu3UZYdNfVcKTxWs2inzXmTCHLTmjPPfx6ptoNevFvtxgHzFKw9bd4RsMCFgskWF71wLTgqPHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f97fd54c38d2faa68145f98e40816e32420fc0d58fc613c984de39a49a55a7","last_reissued_at":"2026-07-05T08:09:30.574494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:30.574494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10662","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":"2026-07-05T08:09:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WbmcT5nDtCcVnI8MGGblaeQeig3ngdufhp2Tfp1zXlcJa9qmCcFa6qz11NVBrIKMojnINUC7S8/w/78BSSsNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:26:22.336350Z"},"content_sha256":"d6790e016728a8dcc1ef5335f81bc5941f087868f64f681ad034c7a7c41e72bb","schema_version":"1.0","event_id":"sha256:d6790e016728a8dcc1ef5335f81bc5941f087868f64f681ad034c7a7c41e72bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WL4X7VKMHDJPVJUBIX4Y4QEBNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chunlin Chen, Jinmei Liu, Shilin Zhang, Wenbin Li, Xiangyu Yue, Zhi Wang","submitted_at":"2024-04-16T15:39:11Z","abstract_excerpt":"We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains previous knowledge by concurrent replay of generated pseudo-data. First, we decouple the continual learning policy into a diffusion-based generative behavior model and a multi-head action evaluation model, allowing the policy to inherit distributional expressivity for encompassing a progressive range of diverse behaviors. Second, we train a task-conditioned d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10662","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/2404.10662/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":"2026-07-05T08:09:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jmv+WbQMNOIfAJ1crk/aW+wRGe6bF50hQX4P/rieQHwSdjofyzdMeQ20rpiSvCtUDRAs4171+ptKeiIrxLbeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:26:22.336902Z"},"content_sha256":"507ef112ba5ca1721221846e202c5a265c47b7119d92c6ea3b4fafd2fb60e3a9","schema_version":"1.0","event_id":"sha256:507ef112ba5ca1721221846e202c5a265c47b7119d92c6ea3b4fafd2fb60e3a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY/bundle.json","state_url":"https://pith.science/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY/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":"2026-08-15T06:26:22Z","links":{"resolver":"https://pith.science/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY","bundle":"https://pith.science/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY/bundle.json","state":"https://pith.science/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WL4X7VKMHDJPVJUBIX4Y4QEBNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WL4X7VKMHDJPVJUBIX4Y4QEBNY","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":"91134db7a5517bbb99c43801932015bcd837062e4573b36e116fab646864595f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:39:11Z","title_canon_sha256":"f96f779eab56d748d13fd1b0ef9cae7eb4b8106fcef7fa847f3e82a7649c2c8f"},"schema_version":"1.0","source":{"id":"2404.10662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10662","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10662v2","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10662","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"WL4X7VKMHDJP","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"WL4X7VKMHDJPVJUB","created_at":"2026-07-05T08:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"WL4X7VKM","created_at":"2026-07-05T08:09:30Z"}],"graph_snapshots":[{"event_id":"sha256:507ef112ba5ca1721221846e202c5a265c47b7119d92c6ea3b4fafd2fb60e3a9","target":"graph","created_at":"2026-07-05T08:09:30Z","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/2404.10662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains previous knowledge by concurrent replay of generated pseudo-data. First, we decouple the continual learning policy into a diffusion-based generative behavior model and a multi-head action evaluation model, allowing the policy to inherit distributional expressivity for encompassing a progressive range of diverse behaviors. Second, we train a task-conditioned d","authors_text":"Chunlin Chen, Jinmei Liu, Shilin Zhang, Wenbin Li, Xiangyu Yue, Zhi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:39:11Z","title":"Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10662","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:d6790e016728a8dcc1ef5335f81bc5941f087868f64f681ad034c7a7c41e72bb","target":"record","created_at":"2026-07-05T08:09:30Z","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":"91134db7a5517bbb99c43801932015bcd837062e4573b36e116fab646864595f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:39:11Z","title_canon_sha256":"f96f779eab56d748d13fd1b0ef9cae7eb4b8106fcef7fa847f3e82a7649c2c8f"},"schema_version":"1.0","source":{"id":"2404.10662","kind":"arxiv","version":2}},"canonical_sha256":"b2f97fd54c38d2faa68145f98e40816e32420fc0d58fc613c984de39a49a55a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2f97fd54c38d2faa68145f98e40816e32420fc0d58fc613c984de39a49a55a7","first_computed_at":"2026-07-05T08:09:30.574494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:30.574494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHpZQhAOw8Slu3UZYdNfVcKTxWs2inzXmTCHLTmjPPfx6ptoNevFvtxgHzFKw9bd4RsMCFgskWF71wLTgqPHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:30.574928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6790e016728a8dcc1ef5335f81bc5941f087868f64f681ad034c7a7c41e72bb","sha256:507ef112ba5ca1721221846e202c5a265c47b7119d92c6ea3b4fafd2fb60e3a9"],"state_sha256":"c66da9e6ef524f9b89d3f64d224fb768472aa2870e376213bc58eed9d39eac8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lAdJTflamtYwrvK2btR+ooLtfrOG/rbuQGcfqbWfBkwyvgj0akLVsg/SihT3QMGxxp5QcNNHhiqDd3NuZeK1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:26:22.341007Z","bundle_sha256":"12f83118d822ccd272d9938c2cb51a33690bab0313f2236ccb587ad5bcb8fc85"}}