{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HLYNMDNWGELBXBW3IXB2YCX3C3","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":"b7bfe73f3377f37d9a3ab421dc08dbba803dc12c2b08add5fe6aca038ce8d371","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-17T12:34:37Z","title_canon_sha256":"72d49f8638948d8356f91014551f5480fc7432a69ffb96c15376db86e1ef9496"},"schema_version":"1.0","source":{"id":"2410.13490","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13490","created_at":"2026-07-05T09:22:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13490v1","created_at":"2026-07-05T09:22:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13490","created_at":"2026-07-05T09:22:01Z"},{"alias_kind":"pith_short_12","alias_value":"HLYNMDNWGELB","created_at":"2026-07-05T09:22:01Z"},{"alias_kind":"pith_short_16","alias_value":"HLYNMDNWGELBXBW3","created_at":"2026-07-05T09:22:01Z"},{"alias_kind":"pith_short_8","alias_value":"HLYNMDNW","created_at":"2026-07-05T09:22:01Z"}],"graph_snapshots":[{"event_id":"sha256:7d0c07cff7629299e4a406ad378dc1d239887b7ec6f2e320ec11039948450b5a","target":"graph","created_at":"2026-07-05T09:22:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.13490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, agents collect state information and rewards through environmental interactions, essential for policy refinement. This process is notably time-consuming, especially in complex robotic simulations and real-world applications. Traditional algorithms usually re-engage with the environment after processing a single batch of samples, thereby failing to fully capitalize on historical data. However, frequently observed states, with reliable value estimates, require minimal updates; in contrast, rare observed states necessitate more intensive updates for achieving accurate v","authors_text":"Houde Liu, Kai Yang, Ke Duan, Xueqian Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-17T12:34:37Z","title":"Novelty-based Sample Reuse for Continuous Robotics Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13490","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:d870f7fa712e02571d5e62300a6579a3c9f426b83e19d1825dae9545f10cd2be","target":"record","created_at":"2026-07-05T09:22:01Z","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":"b7bfe73f3377f37d9a3ab421dc08dbba803dc12c2b08add5fe6aca038ce8d371","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-17T12:34:37Z","title_canon_sha256":"72d49f8638948d8356f91014551f5480fc7432a69ffb96c15376db86e1ef9496"},"schema_version":"1.0","source":{"id":"2410.13490","kind":"arxiv","version":1}},"canonical_sha256":"3af0d60db631161b86db45c3ac0afb16f355178c3082b1cb301e94e3606d85a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3af0d60db631161b86db45c3ac0afb16f355178c3082b1cb301e94e3606d85a2","first_computed_at":"2026-07-05T09:22:01.811189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:01.811189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E7k7AEU8YsusnuyM3lnJE7GfTATsk3jdAYzSCwZhMfewWxp3MQly4kQT+xuvlEvPRggbEJSmn1OQ9Jcdfy+qBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:01.811534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13490","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d870f7fa712e02571d5e62300a6579a3c9f426b83e19d1825dae9545f10cd2be","sha256:7d0c07cff7629299e4a406ad378dc1d239887b7ec6f2e320ec11039948450b5a"],"state_sha256":"dbfacb1ab4b40153f56670c3b260fc5812ed79d51835a42f75108ff0fea96982"}