{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H7J5H6LL7GUZ4NFWUSNMGHSNTP","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":"09b2b0826ca0111898d0afcf78eff74a33b40c23e19135d2a6d2f78713ff2208","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T02:09:35Z","title_canon_sha256":"e9e32b52c85fd424319c9dd3730011784c3b1a1ca7471d07980d6e798d45f190"},"schema_version":"1.0","source":{"id":"2501.18093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18093","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18093v1","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18093","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"H7J5H6LL7GUZ","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"H7J5H6LL7GUZ4NFW","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"H7J5H6LL","created_at":"2026-07-05T10:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:893f0104fe5c76902951285a0595db8346a70c0a2325587c9887e155b89a5905","target":"graph","created_at":"2026-07-05T10:07:06Z","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/2501.18093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the algorithm to learn from a diverse range of interactions rather than just the most recent ones. This buffer is especially essential in dynamic environments with limited experiences. However, efficiently selecting high-value experiences to accelerate training remains a challenge. Drawing inspiration from the role of reward prediction errors (RPEs) in biological ","authors_text":"Bruce A. MacDonald, Henry Williams, Hoda Yamani, Lee Violet C. Ong, Yuning Xing","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T02:09:35Z","title":"Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18093","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":"sha256:0f78143b50bdf8cdb2d55d738def56a389c0a8b8b1afb33aad0de9caf31b45d2","target":"record","created_at":"2026-07-05T10:07:06Z","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":"09b2b0826ca0111898d0afcf78eff74a33b40c23e19135d2a6d2f78713ff2208","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T02:09:35Z","title_canon_sha256":"e9e32b52c85fd424319c9dd3730011784c3b1a1ca7471d07980d6e798d45f190"},"schema_version":"1.0","source":{"id":"2501.18093","kind":"arxiv","version":1}},"canonical_sha256":"3fd3d3f96bf9a99e34b6a49ac31e4d9beb89028a6180d9ac7e77edcdd8f8cc51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fd3d3f96bf9a99e34b6a49ac31e4d9beb89028a6180d9ac7e77edcdd8f8cc51","first_computed_at":"2026-07-05T10:07:06.937672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:06.937672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2eXp84OvA1NGm0QRhbGyOK5vKtF7hQIMt0aIIoJhvswRKyYDaAfirKpwe9IyL59yz1LiLf7vQPiTEnITNPi+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:06.938149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f78143b50bdf8cdb2d55d738def56a389c0a8b8b1afb33aad0de9caf31b45d2","sha256:893f0104fe5c76902951285a0595db8346a70c0a2325587c9887e155b89a5905"],"state_sha256":"061754b6ca7f3de71264b016ccb3c75548303f076517d3cd6b30b5c45abd090f"}