{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZLBR2VOO3IR74D5VZF2P5DIKWT","short_pith_number":"pith:ZLBR2VOO","canonical_record":{"source":{"id":"2408.13452","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-24T03:43:35Z","cross_cats_sorted":[],"title_canon_sha256":"6634f82e26880f492016172742bb4679733f8db5b30f8c593dfc364cb3050876","abstract_canon_sha256":"f39861b671f6ef4e1ba8e87cc6a61f3f04c56a1e8fa5ce86e24402e81eec3f8c"},"schema_version":"1.0"},"canonical_sha256":"cac31d55ceda23fe0fb5c974fe8d0ab4d7de2a4e632a2722196a6068d143e6be","source":{"kind":"arxiv","id":"2408.13452","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13452","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13452v3","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13452","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZLBR2VOO3IR7","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZLBR2VOO3IR74D5V","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZLBR2VOO","created_at":"2026-07-05T09:21:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZLBR2VOO3IR74D5VZF2P5DIKWT","target":"record","payload":{"canonical_record":{"source":{"id":"2408.13452","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-24T03:43:35Z","cross_cats_sorted":[],"title_canon_sha256":"6634f82e26880f492016172742bb4679733f8db5b30f8c593dfc364cb3050876","abstract_canon_sha256":"f39861b671f6ef4e1ba8e87cc6a61f3f04c56a1e8fa5ce86e24402e81eec3f8c"},"schema_version":"1.0"},"canonical_sha256":"cac31d55ceda23fe0fb5c974fe8d0ab4d7de2a4e632a2722196a6068d143e6be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:28.098252Z","signature_b64":"+Uswu6tZYChtNRshMayBQBKgp4QhZPrxmmfYvdF096w7aQGs878lBAqp/149vVJBFmRuO/sevfkYFf+eJ4rCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cac31d55ceda23fe0fb5c974fe8d0ab4d7de2a4e632a2722196a6068d143e6be","last_reissued_at":"2026-07-05T09:21:28.097781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:28.097781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.13452","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":"2026-07-05T09:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HAV6g28/RLM6jQGSEkWVTeNGs5QJfo2ya5gCsLbfSW8WoD0+Xwb0cU43v8ifouAzPTRL+YPSmMda+vYXIJxPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:25:28.023417Z"},"content_sha256":"5b334969f6c4863c81fcac41e2d62bb7dfe682a82059cec77a623de2925bbf7f","schema_version":"1.0","event_id":"sha256:5b334969f6c4863c81fcac41e2d62bb7dfe682a82059cec77a623de2925bbf7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZLBR2VOO3IR74D5VZF2P5DIKWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sihao Wu, Xiaowei Huang, Xingyu Zhao","submitted_at":"2024-08-24T03:43:35Z","abstract_excerpt":"Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary, sequential tasks and is required to learn new tasks without forgetting previous knowledge. However, there is little work on implementing data augmentation for continual RL. In this paper, we investigate the efficacy of data augmentation for continual RL. Specifically, we provide benchmarking data augmentations for continual RL, by (1) summarising existing dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13452","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/2408.13452/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":"2026-07-05T09:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvl2NL3qomysZcBPfovbv9WqYAMxtYustGu5lo5Eftj7Zg7vlaT8CvK85lB0ySiIT2sEaaOMo7eYeZEGRLy6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:25:28.024178Z"},"content_sha256":"b16d8f4ed8088d3e194f479df20cb45620cf37b7bd3de0ed6b0c878a1d256355","schema_version":"1.0","event_id":"sha256:b16d8f4ed8088d3e194f479df20cb45620cf37b7bd3de0ed6b0c878a1d256355"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT/bundle.json","state_url":"https://pith.science/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT/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":"2026-08-22T10:25:28Z","links":{"resolver":"https://pith.science/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT","bundle":"https://pith.science/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT/bundle.json","state":"https://pith.science/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLBR2VOO3IR74D5VZF2P5DIKWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZLBR2VOO3IR74D5VZF2P5DIKWT","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":"f39861b671f6ef4e1ba8e87cc6a61f3f04c56a1e8fa5ce86e24402e81eec3f8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-24T03:43:35Z","title_canon_sha256":"6634f82e26880f492016172742bb4679733f8db5b30f8c593dfc364cb3050876"},"schema_version":"1.0","source":{"id":"2408.13452","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13452","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13452v3","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13452","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZLBR2VOO3IR7","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZLBR2VOO3IR74D5V","created_at":"2026-07-05T09:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZLBR2VOO","created_at":"2026-07-05T09:21:28Z"}],"graph_snapshots":[{"event_id":"sha256:b16d8f4ed8088d3e194f479df20cb45620cf37b7bd3de0ed6b0c878a1d256355","target":"graph","created_at":"2026-07-05T09:21:28Z","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/2408.13452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary, sequential tasks and is required to learn new tasks without forgetting previous knowledge. However, there is little work on implementing data augmentation for continual RL. In this paper, we investigate the efficacy of data augmentation for continual RL. Specifically, we provide benchmarking data augmentations for continual RL, by (1) summarising existing dat","authors_text":"Sihao Wu, Xiaowei Huang, Xingyu Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-24T03:43:35Z","title":"Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13452","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":"sha256:5b334969f6c4863c81fcac41e2d62bb7dfe682a82059cec77a623de2925bbf7f","target":"record","created_at":"2026-07-05T09:21:28Z","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":"f39861b671f6ef4e1ba8e87cc6a61f3f04c56a1e8fa5ce86e24402e81eec3f8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-24T03:43:35Z","title_canon_sha256":"6634f82e26880f492016172742bb4679733f8db5b30f8c593dfc364cb3050876"},"schema_version":"1.0","source":{"id":"2408.13452","kind":"arxiv","version":3}},"canonical_sha256":"cac31d55ceda23fe0fb5c974fe8d0ab4d7de2a4e632a2722196a6068d143e6be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cac31d55ceda23fe0fb5c974fe8d0ab4d7de2a4e632a2722196a6068d143e6be","first_computed_at":"2026-07-05T09:21:28.097781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:28.097781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Uswu6tZYChtNRshMayBQBKgp4QhZPrxmmfYvdF096w7aQGs878lBAqp/149vVJBFmRuO/sevfkYFf+eJ4rCAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:28.098252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13452","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b334969f6c4863c81fcac41e2d62bb7dfe682a82059cec77a623de2925bbf7f","sha256:b16d8f4ed8088d3e194f479df20cb45620cf37b7bd3de0ed6b0c878a1d256355"],"state_sha256":"e98260ff38c6ecd352aa86db1e5c81521a857503b1f5e8f3dbf0c19f8ff5df92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DF16eoOboW0pdheO0jpekqgDj8C13RLLl0p95QvtLLVf0gETnPa/oRFpCRg0Nw6YKSgkkl/q+ZXT9HGbfbgUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T10:25:28.029903Z","bundle_sha256":"8fd777ede73c66d8cb79dff65d832593ab66cbe1f5a5e19dc8ada0089c00c53b"}}