{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HLYNMDNWGELBXBW3IXB2YCX3C3","short_pith_number":"pith:HLYNMDNW","schema_version":"1.0","canonical_sha256":"3af0d60db631161b86db45c3ac0afb16f355178c3082b1cb301e94e3606d85a2","source":{"kind":"arxiv","id":"2410.13490","version":1},"attestation_state":"computed","paper":{"title":"Novelty-based Sample Reuse for Continuous Robotics Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Houde Liu, Kai Yang, Ke Duan, Xueqian Wang","submitted_at":"2024-10-17T12:34:37Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.13490","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-17T12:34:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"72d49f8638948d8356f91014551f5480fc7432a69ffb96c15376db86e1ef9496","abstract_canon_sha256":"b7bfe73f3377f37d9a3ab421dc08dbba803dc12c2b08add5fe6aca038ce8d371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:01.811534Z","signature_b64":"E7k7AEU8YsusnuyM3lnJE7GfTATsk3jdAYzSCwZhMfewWxp3MQly4kQT+xuvlEvPRggbEJSmn1OQ9Jcdfy+qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3af0d60db631161b86db45c3ac0afb16f355178c3082b1cb301e94e3606d85a2","last_reissued_at":"2026-07-05T09:22:01.811189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:01.811189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Novelty-based Sample Reuse for Continuous Robotics Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Houde Liu, Kai Yang, Ke Duan, Xueqian Wang","submitted_at":"2024-10-17T12:34:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13490","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13490/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.13490","created_at":"2026-07-05T09:22:01.811244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13490v1","created_at":"2026-07-05T09:22:01.811244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13490","created_at":"2026-07-05T09:22:01.811244+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLYNMDNWGELB","created_at":"2026-07-05T09:22:01.811244+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLYNMDNWGELBXBW3","created_at":"2026-07-05T09:22:01.811244+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLYNMDNW","created_at":"2026-07-05T09:22:01.811244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15517","citing_title":"Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3","json":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3.json","graph_json":"https://pith.science/api/pith-number/HLYNMDNWGELBXBW3IXB2YCX3C3/graph.json","events_json":"https://pith.science/api/pith-number/HLYNMDNWGELBXBW3IXB2YCX3C3/events.json","paper":"https://pith.science/paper/HLYNMDNW"},"agent_actions":{"view_html":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3","download_json":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3.json","view_paper":"https://pith.science/paper/HLYNMDNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13490&json=true","fetch_graph":"https://pith.science/api/pith-number/HLYNMDNWGELBXBW3IXB2YCX3C3/graph.json","fetch_events":"https://pith.science/api/pith-number/HLYNMDNWGELBXBW3IXB2YCX3C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3/action/storage_attestation","attest_author":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3/action/author_attestation","sign_citation":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3/action/citation_signature","submit_replication":"https://pith.science/pith/HLYNMDNWGELBXBW3IXB2YCX3C3/action/replication_record"}},"created_at":"2026-07-05T09:22:01.811244+00:00","updated_at":"2026-07-05T09:22:01.811244+00:00"}