{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HZWMJ46K2O6CHGC6YYTF4J5FSN","short_pith_number":"pith:HZWMJ46K","schema_version":"1.0","canonical_sha256":"3e6cc4f3cad3bc23985ec6265e27a5934a2987d8296956e7eeb0254bf5a6b662","source":{"kind":"arxiv","id":"2507.14444","version":1},"attestation_state":"computed","paper":{"title":"Statistical and Algorithmic Foundations of Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2025-07-19T02:42:41Z","abstract_excerpt":"As a paradigm for sequential decision making in unknown environments, reinforcement learning (RL) has received a flurry of attention in recent years. However, the explosion of model complexity in emerging applications and the presence of nonconvexity exacerbate the challenge of achieving efficient RL in sample-starved situations, where data collection is expensive, time-consuming, or even high-stakes (e.g., in clinical trials, autonomous systems, and online advertising). How to understand and enhance the sample and computational efficacies of RL algorithms is thus of great interest. In this tu"},"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":"2507.14444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-19T02:42:41Z","cross_cats_sorted":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"6f385283fb096a8f43ff04acfaac7ad9a8ed4bcbee838901f50759fe2d7f961a","abstract_canon_sha256":"829271afb10a3ddcef4736968bb1d8bc393805517dc6690893e62b592aaf25ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:07.151373Z","signature_b64":"2nHOQINA9j8rW9xyQoTJCaZnfIAGRYIAt4KRdjkmwG8t6tlQqZJHax04JHWt4Z8GYiObolrbArwNcmJA1KlUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e6cc4f3cad3bc23985ec6265e27a5934a2987d8296956e7eeb0254bf5a6b662","last_reissued_at":"2026-07-05T11:40:07.150869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:07.150869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical and Algorithmic Foundations of Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2025-07-19T02:42:41Z","abstract_excerpt":"As a paradigm for sequential decision making in unknown environments, reinforcement learning (RL) has received a flurry of attention in recent years. However, the explosion of model complexity in emerging applications and the presence of nonconvexity exacerbate the challenge of achieving efficient RL in sample-starved situations, where data collection is expensive, time-consuming, or even high-stakes (e.g., in clinical trials, autonomous systems, and online advertising). How to understand and enhance the sample and computational efficacies of RL algorithms is thus of great interest. In this tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14444","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/2507.14444/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":"2507.14444","created_at":"2026-07-05T11:40:07.150929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14444v1","created_at":"2026-07-05T11:40:07.150929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14444","created_at":"2026-07-05T11:40:07.150929+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZWMJ46K2O6C","created_at":"2026-07-05T11:40:07.150929+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZWMJ46K2O6CHGC6","created_at":"2026-07-05T11:40:07.150929+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZWMJ46K","created_at":"2026-07-05T11:40:07.150929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN","json":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN.json","graph_json":"https://pith.science/api/pith-number/HZWMJ46K2O6CHGC6YYTF4J5FSN/graph.json","events_json":"https://pith.science/api/pith-number/HZWMJ46K2O6CHGC6YYTF4J5FSN/events.json","paper":"https://pith.science/paper/HZWMJ46K"},"agent_actions":{"view_html":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN","download_json":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN.json","view_paper":"https://pith.science/paper/HZWMJ46K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14444&json=true","fetch_graph":"https://pith.science/api/pith-number/HZWMJ46K2O6CHGC6YYTF4J5FSN/graph.json","fetch_events":"https://pith.science/api/pith-number/HZWMJ46K2O6CHGC6YYTF4J5FSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/action/storage_attestation","attest_author":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/action/author_attestation","sign_citation":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/action/citation_signature","submit_replication":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/action/replication_record"}},"created_at":"2026-07-05T11:40:07.150929+00:00","updated_at":"2026-07-05T11:40:07.150929+00:00"}