{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HDMAL5CAOZHLPXRNZRTLTIX4ZW","short_pith_number":"pith:HDMAL5CA","canonical_record":{"source":{"id":"1810.08163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T17:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5920a5261091efac7ccf22bdd32543594d3dae9bdfa1182e35e1c19704456981","abstract_canon_sha256":"deee04dc6ebc34e1edc4edb504211ed5574fe36d322645e3fd42723968534415"},"schema_version":"1.0"},"canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","source":{"kind":"arxiv","id":"1810.08163","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08163","created_at":"2026-05-18T00:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08163v1","created_at":"2026-05-18T00:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08163","created_at":"2026-05-18T00:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"HDMAL5CAOZHL","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HDMAL5CAOZHLPXRN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HDMAL5CA","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HDMAL5CAOZHLPXRNZRTLTIX4ZW","target":"record","payload":{"canonical_record":{"source":{"id":"1810.08163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T17:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5920a5261091efac7ccf22bdd32543594d3dae9bdfa1182e35e1c19704456981","abstract_canon_sha256":"deee04dc6ebc34e1edc4edb504211ed5574fe36d322645e3fd42723968534415"},"schema_version":"1.0"},"canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:50.410486Z","signature_b64":"2QlZAIey9JvZae9Xm3pdqqfCPbYBuSqnx+NeXzC71DSotCGj1FLZJsBU8u5HWle4mULjYg7RKcmCdEWdjzYtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","last_reissued_at":"2026-05-18T00:02:50.409991Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:50.409991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.08163","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":"2026-05-18T00:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RuUFGYqxKu3WW9t8wA4w5Wf32kXrZE5USIs1/DpB7XL4WSD/ITndvoEJ0cFt1Es0dZHT1vDefXMorvKj3lNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:41:35.080268Z"},"content_sha256":"319dc938c2411999d5f7f6167c48b4f56fe1d61d47d35e7e1da3723186f36caa","schema_version":"1.0","event_id":"sha256:319dc938c2411999d5f7f6167c48b4f56fe1d61d47d35e7e1da3723186f36caa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HDMAL5CAOZHLPXRNZRTLTIX4ZW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast deep reinforcement learning using online adjustments from the past","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Pritzel, Andr\\'e Barreto, Charles Blundell, Pablo Sprechmann, Steven Hansen","submitted_at":"2018-10-18T17:00:20Z","abstract_excerpt":"We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVAis performant on a demonstration task and Atari games."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08163","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":""},"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":"2026-05-18T00:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jhrpmZabIRHFmYbTmY+ISgDyjxBbOPAOLy3aygj58pI3WaBX5VaUGKsX8Kx4tZTRjmnSpXrvRnhBjvzUoIZBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:41:35.080635Z"},"content_sha256":"31d859174596a75f5e231658bc7edbe3ae9ff34025aec2821aec1ad9dfdea317","schema_version":"1.0","event_id":"sha256:31d859174596a75f5e231658bc7edbe3ae9ff34025aec2821aec1ad9dfdea317"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/bundle.json","state_url":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/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":"2026-06-05T00:41:35Z","links":{"resolver":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW","bundle":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/bundle.json","state":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HDMAL5CAOZHLPXRNZRTLTIX4ZW","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":"deee04dc6ebc34e1edc4edb504211ed5574fe36d322645e3fd42723968534415","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T17:00:20Z","title_canon_sha256":"5920a5261091efac7ccf22bdd32543594d3dae9bdfa1182e35e1c19704456981"},"schema_version":"1.0","source":{"id":"1810.08163","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08163","created_at":"2026-05-18T00:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08163v1","created_at":"2026-05-18T00:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08163","created_at":"2026-05-18T00:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"HDMAL5CAOZHL","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HDMAL5CAOZHLPXRN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HDMAL5CA","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:31d859174596a75f5e231658bc7edbe3ae9ff34025aec2821aec1ad9dfdea317","target":"graph","created_at":"2026-05-18T00:02:50Z","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"},"paper":{"abstract_excerpt":"We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVAis performant on a demonstration task and Atari games.","authors_text":"Alexander Pritzel, Andr\\'e Barreto, Charles Blundell, Pablo Sprechmann, Steven Hansen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T17:00:20Z","title":"Fast deep reinforcement learning using online adjustments from the past"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08163","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":"sha256:319dc938c2411999d5f7f6167c48b4f56fe1d61d47d35e7e1da3723186f36caa","target":"record","created_at":"2026-05-18T00:02:50Z","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":"deee04dc6ebc34e1edc4edb504211ed5574fe36d322645e3fd42723968534415","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T17:00:20Z","title_canon_sha256":"5920a5261091efac7ccf22bdd32543594d3dae9bdfa1182e35e1c19704456981"},"schema_version":"1.0","source":{"id":"1810.08163","kind":"arxiv","version":1}},"canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","first_computed_at":"2026-05-18T00:02:50.409991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:50.409991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2QlZAIey9JvZae9Xm3pdqqfCPbYBuSqnx+NeXzC71DSotCGj1FLZJsBU8u5HWle4mULjYg7RKcmCdEWdjzYtDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:50.410486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.08163","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:319dc938c2411999d5f7f6167c48b4f56fe1d61d47d35e7e1da3723186f36caa","sha256:31d859174596a75f5e231658bc7edbe3ae9ff34025aec2821aec1ad9dfdea317"],"state_sha256":"3afb137c9a827af538ffa412ccb73c052802933eb126ff86837ddce910b35c09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLB0NXfrbfD6XCOrAdJc4RcOsLlWYItEcwVkaiYOA+o1epnVH7dHuRoapTCiemwsiiP4KVHuZyvSb8pJFlvwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:41:35.082592Z","bundle_sha256":"7735ac0ce5b5b61f3d57bdfc153f52b80ba9f873768a010da24025c6f1d0fe0e"}}