{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HNWSYLAC2ULR5RZSEZ5IB7EHJK","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":"1fa57b01927db188fed8ed96e00912cc876895853053088a0115e76e7562d2b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T14:03:23Z","title_canon_sha256":"b653cdb652ef849d19fa8936dca293949ea0572da52dc77a6aad2c82924319d5"},"schema_version":"1.0","source":{"id":"2411.10809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10809","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10809v1","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10809","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"HNWSYLAC2ULR","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"HNWSYLAC2ULR5RZS","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"HNWSYLAC","created_at":"2026-07-05T09:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:775ec16a4e1b2c9dca01811aef06cfcbd18f3d52d396ad56448326cbbfbae247","target":"graph","created_at":"2026-07-05T09:36:22Z","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/2411.10809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this problem setting, a pivotal challenge revolves around \\textit{catastrophic forgetting} issue, wherein the agent is prone to effortlessly erode the decisional knowledge associated with past encountered tasks when learning the new one. In recent progresses, the \\textit{generative replay} methods have showcased substantial potential by employing generative models t","authors_text":"Cong Guan, Feng Chen, Fuguang Han, Lei Yuan, Yang Yu, Zhilong Zhang, Zongzhang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T14:03:23Z","title":"Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10809","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:da043efb94047e2208f6a2d438bf5112c2d7a5d74c6202142e5b5425ee1107ca","target":"record","created_at":"2026-07-05T09:36:22Z","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":"1fa57b01927db188fed8ed96e00912cc876895853053088a0115e76e7562d2b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T14:03:23Z","title_canon_sha256":"b653cdb652ef849d19fa8936dca293949ea0572da52dc77a6aad2c82924319d5"},"schema_version":"1.0","source":{"id":"2411.10809","kind":"arxiv","version":1}},"canonical_sha256":"3b6d2c2c02d5171ec732267a80fc874ab6cf9d1738ed0f9094b75bd9f01edf06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b6d2c2c02d5171ec732267a80fc874ab6cf9d1738ed0f9094b75bd9f01edf06","first_computed_at":"2026-07-05T09:36:22.519806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:22.519806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3uxqBlAgZqhSWt9GsR3xaJR0Hkn0ZD/r59qJjznYBW+m8gb2ebDoH7zdumr8yoZHeMzBFTI2Pwcg8icqobxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:22.520271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da043efb94047e2208f6a2d438bf5112c2d7a5d74c6202142e5b5425ee1107ca","sha256:775ec16a4e1b2c9dca01811aef06cfcbd18f3d52d396ad56448326cbbfbae247"],"state_sha256":"449bd1864610336c7ae2bb1b04ba284e7179b2f1b1221862519ae5356e158edd"}