{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:C33MRJK663FICA35N72CMJ4K7C","short_pith_number":"pith:C33MRJK6","canonical_record":{"source":{"id":"1806.00540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T20:52:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f22e597ae34ebf87a278692c0e92c6fef7d7ba0814b0c90886247274df25ff18","abstract_canon_sha256":"1ea30bb39dc6b0919501f140f0a530121cad8a5d5a901735b32afe89675b7bee"},"schema_version":"1.0"},"canonical_sha256":"16f6c8a55ef6ca81037d6ff426278af8adff55aecbc584a5f207ff5fdcf3254c","source":{"kind":"arxiv","id":"1806.00540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00540","created_at":"2026-05-18T00:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00540v1","created_at":"2026-05-18T00:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00540","created_at":"2026-05-18T00:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"C33MRJK663FI","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C33MRJK663FICA35","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C33MRJK6","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:C33MRJK663FICA35N72CMJ4K7C","target":"record","payload":{"canonical_record":{"source":{"id":"1806.00540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T20:52:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f22e597ae34ebf87a278692c0e92c6fef7d7ba0814b0c90886247274df25ff18","abstract_canon_sha256":"1ea30bb39dc6b0919501f140f0a530121cad8a5d5a901735b32afe89675b7bee"},"schema_version":"1.0"},"canonical_sha256":"16f6c8a55ef6ca81037d6ff426278af8adff55aecbc584a5f207ff5fdcf3254c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:19.061346Z","signature_b64":"V60MeDnM1nWSlLDlDXqUaQafYX/LKEhxiUo5B4vAInHd8QBws0IvHQuTPjcI6131d8cHKxyaVirzRQCQfHbtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16f6c8a55ef6ca81037d6ff426278af8adff55aecbc584a5f207ff5fdcf3254c","last_reissued_at":"2026-05-18T00:14:19.060758Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:19.060758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.00540","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":"2026-05-18T00:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RDW2Yc/Ux4162Qwp7aX9P3MrtJ0cVEIwp2Y2a1TvYuuPlVz3TwbGeUmFvdLHKMA3tO15wNnWO2icN8g/qddCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:24:18.228181Z"},"content_sha256":"4f54a996e7c8b72de06c4bb433195c31183f191a86a07e7265abf02622906895","schema_version":"1.0","event_id":"sha256:4f54a996e7c8b72de06c4bb433195c31183f191a86a07e7265abf02622906895"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:C33MRJK663FICA35N72CMJ4K7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenny J. Young, Richard S. Sutton, Shuo Yang","submitted_at":"2018-06-01T20:52:31Z","abstract_excerpt":"Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered information is found to be useful. Inspired by this idea, and the increasing popularity of external memory mechanisms to handle long-term dependencies in deep learning systems, we propose a novel algorithm which uses a reservoir sampling procedure to maintain an external memory consisting of a fixed number of past states. The algorithm allows a deep reinforc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00540","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":"2026-05-18T00:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wMlQF1R2lZbzJx/NRcwpy2ASuSSGLDLUjAUdKCwOKKtYUC539R5I4H4Wqujc0JPP5pPh4SEC07ocGfu2tj6FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:24:18.228967Z"},"content_sha256":"2672eec8b81b7ea6072615d52a921edc95dd93972af451fabbc625cbf46f283c","schema_version":"1.0","event_id":"sha256:2672eec8b81b7ea6072615d52a921edc95dd93972af451fabbc625cbf46f283c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C33MRJK663FICA35N72CMJ4K7C/bundle.json","state_url":"https://pith.science/pith/C33MRJK663FICA35N72CMJ4K7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C33MRJK663FICA35N72CMJ4K7C/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":"2026-05-31T23:24:18Z","links":{"resolver":"https://pith.science/pith/C33MRJK663FICA35N72CMJ4K7C","bundle":"https://pith.science/pith/C33MRJK663FICA35N72CMJ4K7C/bundle.json","state":"https://pith.science/pith/C33MRJK663FICA35N72CMJ4K7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C33MRJK663FICA35N72CMJ4K7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:C33MRJK663FICA35N72CMJ4K7C","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":"1ea30bb39dc6b0919501f140f0a530121cad8a5d5a901735b32afe89675b7bee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T20:52:31Z","title_canon_sha256":"f22e597ae34ebf87a278692c0e92c6fef7d7ba0814b0c90886247274df25ff18"},"schema_version":"1.0","source":{"id":"1806.00540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00540","created_at":"2026-05-18T00:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00540v1","created_at":"2026-05-18T00:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00540","created_at":"2026-05-18T00:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"C33MRJK663FI","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C33MRJK663FICA35","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C33MRJK6","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:2672eec8b81b7ea6072615d52a921edc95dd93972af451fabbc625cbf46f283c","target":"graph","created_at":"2026-05-18T00:14:19Z","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":"Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered information is found to be useful. Inspired by this idea, and the increasing popularity of external memory mechanisms to handle long-term dependencies in deep learning systems, we propose a novel algorithm which uses a reservoir sampling procedure to maintain an external memory consisting of a fixed number of past states. The algorithm allows a deep reinforc","authors_text":"Kenny J. Young, Richard S. Sutton, Shuo Yang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T20:52:31Z","title":"Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00540","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":"sha256:4f54a996e7c8b72de06c4bb433195c31183f191a86a07e7265abf02622906895","target":"record","created_at":"2026-05-18T00:14:19Z","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":"1ea30bb39dc6b0919501f140f0a530121cad8a5d5a901735b32afe89675b7bee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T20:52:31Z","title_canon_sha256":"f22e597ae34ebf87a278692c0e92c6fef7d7ba0814b0c90886247274df25ff18"},"schema_version":"1.0","source":{"id":"1806.00540","kind":"arxiv","version":1}},"canonical_sha256":"16f6c8a55ef6ca81037d6ff426278af8adff55aecbc584a5f207ff5fdcf3254c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16f6c8a55ef6ca81037d6ff426278af8adff55aecbc584a5f207ff5fdcf3254c","first_computed_at":"2026-05-18T00:14:19.060758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:19.060758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V60MeDnM1nWSlLDlDXqUaQafYX/LKEhxiUo5B4vAInHd8QBws0IvHQuTPjcI6131d8cHKxyaVirzRQCQfHbtAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:19.061346Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f54a996e7c8b72de06c4bb433195c31183f191a86a07e7265abf02622906895","sha256:2672eec8b81b7ea6072615d52a921edc95dd93972af451fabbc625cbf46f283c"],"state_sha256":"4b9f8c099679ddbb9186a4af4b93b505c03bee0bef239a1084b2e5d589d67ea7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dSbPF5+5kHfp1Zq+vsO82T2+ECemM2X/QgdQhdz+t7SdkfoysLOM3vw+17xllIYtmDiIfMmewm3R/2fs76GzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T23:24:18.233525Z","bundle_sha256":"cc045a0ced64630d7b243a7a38374ec207e752d850cd0df795d2dd7acf6d4f8f"}}