{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SB6CUVNEBPXF4YHZUYKLSVOV7I","short_pith_number":"pith:SB6CUVNE","canonical_record":{"source":{"id":"2311.11557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-20T06:21:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"862e933d9a16f9c670264acf980bae9c0280d5ffbb6bb6e4667095d3ceb9b073","abstract_canon_sha256":"71e5b64927fb8c9a295c3a602fd70baef1278bdd74e804712ac8309e6f6d995a"},"schema_version":"1.0"},"canonical_sha256":"907c2a55a40bee5e60f9a614b955d5fa02825e8cd7934f74dfb77faa14e02045","source":{"kind":"arxiv","id":"2311.11557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11557","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11557v1","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11557","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"SB6CUVNEBPXF","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"SB6CUVNEBPXF4YHZ","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"SB6CUVNE","created_at":"2026-07-05T07:14:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SB6CUVNEBPXF4YHZUYKLSVOV7I","target":"record","payload":{"canonical_record":{"source":{"id":"2311.11557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-20T06:21:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"862e933d9a16f9c670264acf980bae9c0280d5ffbb6bb6e4667095d3ceb9b073","abstract_canon_sha256":"71e5b64927fb8c9a295c3a602fd70baef1278bdd74e804712ac8309e6f6d995a"},"schema_version":"1.0"},"canonical_sha256":"907c2a55a40bee5e60f9a614b955d5fa02825e8cd7934f74dfb77faa14e02045","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:35.403597Z","signature_b64":"e2eA0ijVBB02LINKaAay8zouoNhpkjW8jQnr0ujdcqIgQF76WYb8Qrn0/wq1B0W7fUyUR97gCyBFO20TWVtsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"907c2a55a40bee5e60f9a614b955d5fa02825e8cd7934f74dfb77faa14e02045","last_reissued_at":"2026-07-05T07:14:35.403144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:35.403144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.11557","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+eNn8/gp9a7mc3lULVHuwa/KktyiNDZfmuxdU9zp/1gRACHeui4XYLV6sXxoOzDcOWclvfnhIHrfodharI2VBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:46:06.497035Z"},"content_sha256":"f0ad264c60d0dbeb411382646f9592a4b799d26ae00d853300e61388f983a988","schema_version":"1.0","event_id":"sha256:f0ad264c60d0dbeb411382646f9592a4b799d26ae00d853300e61388f983a988"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SB6CUVNEBPXF4YHZUYKLSVOV7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Replay-enhanced Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Deheng Ye, Kevin Zehua Shen, Tiantian Zhang, Xiu Li, Xueqian Wang, Zichuan Lin","submitted_at":"2023-11-20T06:21:52Z","abstract_excerpt":"Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure, when used as a solution to forgetting in continual reinforcement learning, even in the context of perfect memory where all data of previous tasks are accessible in the current task. On the one hand, since most reinforcement learning algorithms are not invariant to the reward scale, the previously well-learned tasks (with high rewards) may appear to be more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11557","kind":"arxiv","version":1},"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/2311.11557/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":"2026-07-05T07:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNOrmKTC0RvsGP1i55Y+A3cL7n3lGG/AnkQ4KgPuiqHvP6qoJMO4vLsvLmdsitmT3iCW9/yoLKQUmgUaquuNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:46:06.497435Z"},"content_sha256":"ebd583de7d159ea85f0277162fe8063be0970ba9dc77fca4580650074aa555c9","schema_version":"1.0","event_id":"sha256:ebd583de7d159ea85f0277162fe8063be0970ba9dc77fca4580650074aa555c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I/bundle.json","state_url":"https://pith.science/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I/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":"2026-08-07T03:46:06Z","links":{"resolver":"https://pith.science/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I","bundle":"https://pith.science/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I/bundle.json","state":"https://pith.science/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SB6CUVNEBPXF4YHZUYKLSVOV7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SB6CUVNEBPXF4YHZUYKLSVOV7I","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":"71e5b64927fb8c9a295c3a602fd70baef1278bdd74e804712ac8309e6f6d995a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-20T06:21:52Z","title_canon_sha256":"862e933d9a16f9c670264acf980bae9c0280d5ffbb6bb6e4667095d3ceb9b073"},"schema_version":"1.0","source":{"id":"2311.11557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11557","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11557v1","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11557","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"SB6CUVNEBPXF","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"SB6CUVNEBPXF4YHZ","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"SB6CUVNE","created_at":"2026-07-05T07:14:35Z"}],"graph_snapshots":[{"event_id":"sha256:ebd583de7d159ea85f0277162fe8063be0970ba9dc77fca4580650074aa555c9","target":"graph","created_at":"2026-07-05T07:14:35Z","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/2311.11557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure, when used as a solution to forgetting in continual reinforcement learning, even in the context of perfect memory where all data of previous tasks are accessible in the current task. On the one hand, since most reinforcement learning algorithms are not invariant to the reward scale, the previously well-learned tasks (with high rewards) may appear to be more ","authors_text":"Bo Yuan, Deheng Ye, Kevin Zehua Shen, Tiantian Zhang, Xiu Li, Xueqian Wang, Zichuan Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-20T06:21:52Z","title":"Replay-enhanced Continual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11557","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:f0ad264c60d0dbeb411382646f9592a4b799d26ae00d853300e61388f983a988","target":"record","created_at":"2026-07-05T07:14:35Z","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":"71e5b64927fb8c9a295c3a602fd70baef1278bdd74e804712ac8309e6f6d995a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-20T06:21:52Z","title_canon_sha256":"862e933d9a16f9c670264acf980bae9c0280d5ffbb6bb6e4667095d3ceb9b073"},"schema_version":"1.0","source":{"id":"2311.11557","kind":"arxiv","version":1}},"canonical_sha256":"907c2a55a40bee5e60f9a614b955d5fa02825e8cd7934f74dfb77faa14e02045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"907c2a55a40bee5e60f9a614b955d5fa02825e8cd7934f74dfb77faa14e02045","first_computed_at":"2026-07-05T07:14:35.403144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:35.403144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2eA0ijVBB02LINKaAay8zouoNhpkjW8jQnr0ujdcqIgQF76WYb8Qrn0/wq1B0W7fUyUR97gCyBFO20TWVtsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:35.403597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.11557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0ad264c60d0dbeb411382646f9592a4b799d26ae00d853300e61388f983a988","sha256:ebd583de7d159ea85f0277162fe8063be0970ba9dc77fca4580650074aa555c9"],"state_sha256":"6e5439cd033bed431fe358697238a2b28478ec7e1ebd6ae17afb5b2434fc16a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bJXEDBrV0Ku+/YmYVehC47ft6n9i6oIap/JJw5NVYqKkdxJ97OOir5KsFXs3wIPisu7OlShXUum2slEvLhEGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:46:06.500229Z","bundle_sha256":"572eac661d9ce7bd288f01e23ff7d77df8238bb4819d0b63e3e190f84e1b0cfc"}}