{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:MZHKTPI4P25JGWF753KCKAHU3L","short_pith_number":"pith:MZHKTPI4","canonical_record":{"source":{"id":"1511.05952","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:54:44Z","cross_cats_sorted":[],"title_canon_sha256":"c7fa449cdf7ed99a02d26c8bb7b03bedbfbb8dd789b862b7eb48a35ba0004664","abstract_canon_sha256":"abce482d96085da6ab3e9de627f2cffd47e9211383053b88cbb7d82586547e02"},"schema_version":"1.0"},"canonical_sha256":"664ea9bd1c7eba9358bfeed42500f4dad6d42931d7f3e8f7dacf8da7ea57aa4d","source":{"kind":"arxiv","id":"1511.05952","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05952","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05952v4","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05952","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"MZHKTPI4P25J","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"MZHKTPI4P25JGWF7","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"MZHKTPI4","created_at":"2026-05-18T12:29:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:MZHKTPI4P25JGWF753KCKAHU3L","target":"record","payload":{"canonical_record":{"source":{"id":"1511.05952","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:54:44Z","cross_cats_sorted":[],"title_canon_sha256":"c7fa449cdf7ed99a02d26c8bb7b03bedbfbb8dd789b862b7eb48a35ba0004664","abstract_canon_sha256":"abce482d96085da6ab3e9de627f2cffd47e9211383053b88cbb7d82586547e02"},"schema_version":"1.0"},"canonical_sha256":"664ea9bd1c7eba9358bfeed42500f4dad6d42931d7f3e8f7dacf8da7ea57aa4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:01.126092Z","signature_b64":"XJl8D3qf8rDRqrlOS29R/DeUNtigaw10yxllPjvW3/rOHz8V0uQJphRdpe34yvt9n+xCSNH4sCHq1CXcgQQkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664ea9bd1c7eba9358bfeed42500f4dad6d42931d7f3e8f7dacf8da7ea57aa4d","last_reissued_at":"2026-05-18T01:20:01.125362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:01.125362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.05952","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dgNkYcdZMkPlQQBo5iR0W5ZR/P/qsjQOX50YycywArzAsPgZEy2FB+YylRXU27GGZuKX3aqSMRHUoa3zolWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:13:14.806920Z"},"content_sha256":"3a8b31c9d2e2f50a9bc39021f1907aee7d594a3a7ffa56517d41e732fb66ea52","schema_version":"1.0","event_id":"sha256:3a8b31c9d2e2f50a9bc39021f1907aee7d594a3a7ffa56517d41e732fb66ea52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:MZHKTPI4P25JGWF753KCKAHU3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prioritized Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Silver, Ioannis Antonoglou, John Quan, Tom Schaul","submitted_at":"2015-11-18T20:54:44Z","abstract_excerpt":"Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05952","kind":"arxiv","version":4},"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":"2026-05-18T01:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+0xQat7la/a7zNK4Rwom7Yn4p1M9O3hh7laLtSWlZYcdMjtA/cZY27Gfz4pq9XbFAVRTmBnSWzJwW4eqilIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:13:14.807265Z"},"content_sha256":"318e70058b51f2e9d92e4757000832df3fd4d77d662bd85b83e3ba10c8c27e2e","schema_version":"1.0","event_id":"sha256:318e70058b51f2e9d92e4757000832df3fd4d77d662bd85b83e3ba10c8c27e2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZHKTPI4P25JGWF753KCKAHU3L/bundle.json","state_url":"https://pith.science/pith/MZHKTPI4P25JGWF753KCKAHU3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZHKTPI4P25JGWF753KCKAHU3L/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":"2026-06-02T05:13:14Z","links":{"resolver":"https://pith.science/pith/MZHKTPI4P25JGWF753KCKAHU3L","bundle":"https://pith.science/pith/MZHKTPI4P25JGWF753KCKAHU3L/bundle.json","state":"https://pith.science/pith/MZHKTPI4P25JGWF753KCKAHU3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZHKTPI4P25JGWF753KCKAHU3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:MZHKTPI4P25JGWF753KCKAHU3L","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":"abce482d96085da6ab3e9de627f2cffd47e9211383053b88cbb7d82586547e02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:54:44Z","title_canon_sha256":"c7fa449cdf7ed99a02d26c8bb7b03bedbfbb8dd789b862b7eb48a35ba0004664"},"schema_version":"1.0","source":{"id":"1511.05952","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05952","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05952v4","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05952","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"MZHKTPI4P25J","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"MZHKTPI4P25JGWF7","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"MZHKTPI4","created_at":"2026-05-18T12:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:318e70058b51f2e9d92e4757000832df3fd4d77d662bd85b83e3ba10c8c27e2e","target":"graph","created_at":"2026-05-18T01:20:01Z","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":"Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achi","authors_text":"David Silver, Ioannis Antonoglou, John Quan, Tom Schaul","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:54:44Z","title":"Prioritized Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05952","kind":"arxiv","version":4},"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":"sha256:3a8b31c9d2e2f50a9bc39021f1907aee7d594a3a7ffa56517d41e732fb66ea52","target":"record","created_at":"2026-05-18T01:20:01Z","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":"abce482d96085da6ab3e9de627f2cffd47e9211383053b88cbb7d82586547e02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:54:44Z","title_canon_sha256":"c7fa449cdf7ed99a02d26c8bb7b03bedbfbb8dd789b862b7eb48a35ba0004664"},"schema_version":"1.0","source":{"id":"1511.05952","kind":"arxiv","version":4}},"canonical_sha256":"664ea9bd1c7eba9358bfeed42500f4dad6d42931d7f3e8f7dacf8da7ea57aa4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"664ea9bd1c7eba9358bfeed42500f4dad6d42931d7f3e8f7dacf8da7ea57aa4d","first_computed_at":"2026-05-18T01:20:01.125362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:01.125362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJl8D3qf8rDRqrlOS29R/DeUNtigaw10yxllPjvW3/rOHz8V0uQJphRdpe34yvt9n+xCSNH4sCHq1CXcgQQkDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:01.126092Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.05952","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a8b31c9d2e2f50a9bc39021f1907aee7d594a3a7ffa56517d41e732fb66ea52","sha256:318e70058b51f2e9d92e4757000832df3fd4d77d662bd85b83e3ba10c8c27e2e"],"state_sha256":"7f45a8b4eda5c2e23bb5787f6a3d7f65fc541997534e0d0a31fdf8fb6521e1a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NEbFH/I1GSZMZsqG+Fdkauk9Yd0xZFkggeYvLLlzl2LkjhmUdVlpSrJDRVu/oL9vFYRoFjIxHKhaolF47F1dBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:13:14.809207Z","bundle_sha256":"27bb7d3046fc72f644ff75b2797020ecea7d187214483ac107ce5f90452d48d2"}}