{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QUZEHKJFOW4XREBJU6NHTBZJLR","short_pith_number":"pith:QUZEHKJF","canonical_record":{"source":{"id":"2401.16650","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T00:48:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9785176195efe6f53f3eabc2a913266c7cb4a9aa14fb82774b507888053f1fa1","abstract_canon_sha256":"2dc4ba64bdf61f1019abce9f3f68ab18cadaad9de9ec543baabacd6c645388e5"},"schema_version":"1.0"},"canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","source":{"kind":"arxiv","id":"2401.16650","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16650","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16650v3","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16650","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"QUZEHKJFOW4X","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"QUZEHKJFOW4XREBJ","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"QUZEHKJF","created_at":"2026-07-05T08:44:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QUZEHKJFOW4XREBJU6NHTBZJLR","target":"record","payload":{"canonical_record":{"source":{"id":"2401.16650","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T00:48:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9785176195efe6f53f3eabc2a913266c7cb4a9aa14fb82774b507888053f1fa1","abstract_canon_sha256":"2dc4ba64bdf61f1019abce9f3f68ab18cadaad9de9ec543baabacd6c645388e5"},"schema_version":"1.0"},"canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:11.696200Z","signature_b64":"yfFFLJGT3YEB4AGqMnf9SKMVGVBuei+pdBDKup5S3uSirTTHjehmD2eRpcMM1HlxQaJpREs0mvcVHfaXML9LBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","last_reissued_at":"2026-07-05T08:44:11.695714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:11.695714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.16650","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Zlwzamn/Axp7JSx9py5lJOOdmDhPwGmq/YIl0LRU/8PEx+xIe/5u5gtPndJBEMD73IdJpbJSkUOjQBQhDovDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:01:36.989114Z"},"content_sha256":"cf104c5133352de70a05bf7629dabceb960d364bfb5a09a2df79292d6440098e","schema_version":"1.0","event_id":"sha256:cf104c5133352de70a05bf7629dabceb960d364bfb5a09a2df79292d6440098e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QUZEHKJFOW4XREBJU6NHTBZJLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting Replay in World Models for Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gideon Kowadlo, Levin Kuhlmann, Luke Yang","submitted_at":"2024-01-30T00:48:26Z","abstract_excerpt":"Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic forgetting, but often struggle with scalability due to large memory requirements. Biologically inspired replay suggests replay to a world model, aligning with model-based RL; as opposed to the common setting of replay in model-free algorithms. Model-based RL offers benefits for continual RL by leveraging knowledge of the environment, independent of policy. We i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16650","kind":"arxiv","version":3},"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/2401.16650/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":"2026-07-05T08:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfM8oo6FGkIpr0QrVblQBN5rgELHxgrfZo43Hhy6gHUi6s0KxRJHNi0tP5eEwZBr5X67SWUoH1KntHIxLq8zBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:01:36.989716Z"},"content_sha256":"496cc09c6cf91d1b259af75a0ab1d3bf4bb2fea9a1a92daa8b2a39c4e345993f","schema_version":"1.0","event_id":"sha256:496cc09c6cf91d1b259af75a0ab1d3bf4bb2fea9a1a92daa8b2a39c4e345993f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/bundle.json","state_url":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/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":"2026-08-20T06:01:36Z","links":{"resolver":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR","bundle":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/bundle.json","state":"https://pith.science/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUZEHKJFOW4XREBJU6NHTBZJLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QUZEHKJFOW4XREBJU6NHTBZJLR","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":"2dc4ba64bdf61f1019abce9f3f68ab18cadaad9de9ec543baabacd6c645388e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T00:48:26Z","title_canon_sha256":"9785176195efe6f53f3eabc2a913266c7cb4a9aa14fb82774b507888053f1fa1"},"schema_version":"1.0","source":{"id":"2401.16650","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16650","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16650v3","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16650","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"QUZEHKJFOW4X","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"QUZEHKJFOW4XREBJ","created_at":"2026-07-05T08:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"QUZEHKJF","created_at":"2026-07-05T08:44:11Z"}],"graph_snapshots":[{"event_id":"sha256:496cc09c6cf91d1b259af75a0ab1d3bf4bb2fea9a1a92daa8b2a39c4e345993f","target":"graph","created_at":"2026-07-05T08:44:11Z","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/2401.16650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic forgetting, but often struggle with scalability due to large memory requirements. Biologically inspired replay suggests replay to a world model, aligning with model-based RL; as opposed to the common setting of replay in model-free algorithms. Model-based RL offers benefits for continual RL by leveraging knowledge of the environment, independent of policy. We i","authors_text":"Gideon Kowadlo, Levin Kuhlmann, Luke Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T00:48:26Z","title":"Augmenting Replay in World Models for Continual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16650","kind":"arxiv","version":3},"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:cf104c5133352de70a05bf7629dabceb960d364bfb5a09a2df79292d6440098e","target":"record","created_at":"2026-07-05T08:44:11Z","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":"2dc4ba64bdf61f1019abce9f3f68ab18cadaad9de9ec543baabacd6c645388e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T00:48:26Z","title_canon_sha256":"9785176195efe6f53f3eabc2a913266c7cb4a9aa14fb82774b507888053f1fa1"},"schema_version":"1.0","source":{"id":"2401.16650","kind":"arxiv","version":3}},"canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"853243a92575b9789029a79a7987295c7137bb1047dc3941f0ce7544f4b1ebfe","first_computed_at":"2026-07-05T08:44:11.695714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:11.695714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yfFFLJGT3YEB4AGqMnf9SKMVGVBuei+pdBDKup5S3uSirTTHjehmD2eRpcMM1HlxQaJpREs0mvcVHfaXML9LBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:11.696200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16650","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf104c5133352de70a05bf7629dabceb960d364bfb5a09a2df79292d6440098e","sha256:496cc09c6cf91d1b259af75a0ab1d3bf4bb2fea9a1a92daa8b2a39c4e345993f"],"state_sha256":"9dc0e64fae992006f8be14e6c62c24c4a83f266db5255e18a5a415eaa11a3c2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmdbFL26sVSCoag7cbDiD51ERIXJd1l7uFgqlZ7i762Seh1eHzkx09m0RP97Nc+WjuAjdRzcPxElzqi5uAaxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:01:36.994275Z","bundle_sha256":"05525e58fedd64ea92d4cd31920694866f0d8f99b44e844bdb5a29b6ddad7816"}}