{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HZWMJ46K2O6CHGC6YYTF4J5FSN","short_pith_number":"pith:HZWMJ46K","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"},"canonical_sha256":"3e6cc4f3cad3bc23985ec6265e27a5934a2987d8296956e7eeb0254bf5a6b662","source":{"kind":"arxiv","id":"2507.14444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14444","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14444v1","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14444","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"pith_short_12","alias_value":"HZWMJ46K2O6C","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"pith_short_16","alias_value":"HZWMJ46K2O6CHGC6","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"pith_short_8","alias_value":"HZWMJ46K","created_at":"2026-07-05T11:40:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HZWMJ46K2O6CHGC6YYTF4J5FSN","target":"record","payload":{"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"},"canonical_sha256":"3e6cc4f3cad3bc23985ec6265e27a5934a2987d8296956e7eeb0254bf5a6b662","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"},"source_kind":"arxiv","source_id":"2507.14444","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SvTfA961H910Ul9nuJAU/GRXscMPtlXc+NIAzVF6DnlLCt2Jb6Vw6l5vKC6oRXMDkYLDVnfOobib5p5++CHKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:26:00.681990Z"},"content_sha256":"52532f30e23aef34bd80092ec77b24f9241107b43fc1d5043c10ad6b86c49666","schema_version":"1.0","event_id":"sha256:52532f30e23aef34bd80092ec77b24f9241107b43fc1d5043c10ad6b86c49666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HZWMJ46K2O6CHGC6YYTF4J5FSN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3gZ6Ao4vPxI0JGOYuT7A+4VK6ONUY67ETTM9j6PSfIIsUt+LUSzKW7POh564wb9JRtEeln050AZ/Qinx8v6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:26:00.682505Z"},"content_sha256":"04fae6745d1569510d51f60c87b49d1974ec076a415f39122224877d6470d2b1","schema_version":"1.0","event_id":"sha256:04fae6745d1569510d51f60c87b49d1974ec076a415f39122224877d6470d2b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/bundle.json","state_url":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/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":"2026-08-07T04:26:00Z","links":{"resolver":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN","bundle":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/bundle.json","state":"https://pith.science/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZWMJ46K2O6CHGC6YYTF4J5FSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HZWMJ46K2O6CHGC6YYTF4J5FSN","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":"829271afb10a3ddcef4736968bb1d8bc393805517dc6690893e62b592aaf25ec","cross_cats_sorted":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-19T02:42:41Z","title_canon_sha256":"6f385283fb096a8f43ff04acfaac7ad9a8ed4bcbee838901f50759fe2d7f961a"},"schema_version":"1.0","source":{"id":"2507.14444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14444","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14444v1","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14444","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"pith_short_12","alias_value":"HZWMJ46K2O6C","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"pith_short_16","alias_value":"HZWMJ46K2O6CHGC6","created_at":"2026-07-05T11:40:07Z"},{"alias_kind":"pith_short_8","alias_value":"HZWMJ46K","created_at":"2026-07-05T11:40:07Z"}],"graph_snapshots":[{"event_id":"sha256:04fae6745d1569510d51f60c87b49d1974ec076a415f39122224877d6470d2b1","target":"graph","created_at":"2026-07-05T11:40:07Z","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/2507.14444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Yuejie Chi, Yuting Wei, Yuxin Chen","cross_cats":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-19T02:42:41Z","title":"Statistical and Algorithmic Foundations of Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14444","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":"sha256:52532f30e23aef34bd80092ec77b24f9241107b43fc1d5043c10ad6b86c49666","target":"record","created_at":"2026-07-05T11:40:07Z","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":"829271afb10a3ddcef4736968bb1d8bc393805517dc6690893e62b592aaf25ec","cross_cats_sorted":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-19T02:42:41Z","title_canon_sha256":"6f385283fb096a8f43ff04acfaac7ad9a8ed4bcbee838901f50759fe2d7f961a"},"schema_version":"1.0","source":{"id":"2507.14444","kind":"arxiv","version":1}},"canonical_sha256":"3e6cc4f3cad3bc23985ec6265e27a5934a2987d8296956e7eeb0254bf5a6b662","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e6cc4f3cad3bc23985ec6265e27a5934a2987d8296956e7eeb0254bf5a6b662","first_computed_at":"2026-07-05T11:40:07.150869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:07.150869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2nHOQINA9j8rW9xyQoTJCaZnfIAGRYIAt4KRdjkmwG8t6tlQqZJHax04JHWt4Z8GYiObolrbArwNcmJA1KlUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:07.151373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52532f30e23aef34bd80092ec77b24f9241107b43fc1d5043c10ad6b86c49666","sha256:04fae6745d1569510d51f60c87b49d1974ec076a415f39122224877d6470d2b1"],"state_sha256":"fbb31a1e6d20a12bd3d0c31b44fbfe33241f1a3bf3d8931f9dd5e3a7924da0cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TUTKkUkQiCsSdC+OIgDmVrHv96Hwb6kGpudpC8z94wrC03B5tBtBTSqalxPadgfl3mN5sa0dxS6+sEIYe55vAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:26:00.687801Z","bundle_sha256":"64e3d9886f28dd6331654e3938cd2eb13a30cad679510965d7c7ddcd661423bb"}}