{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:A5CJZAB4Z6RLUDXXDO6DSR4LYS","short_pith_number":"pith:A5CJZAB4","canonical_record":{"source":{"id":"2305.19001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-30T12:58:39Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"title_canon_sha256":"93a8bf38a9337355132506131293702559ba0ad5842740f79c3a55e1164df554","abstract_canon_sha256":"89ac4fa4106ed3ee9d7c4dc7059c5dae8530f507f5df819adbdb6c7d1150dafa"},"schema_version":"1.0"},"canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","source":{"kind":"arxiv","id":"2305.19001","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19001","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19001v2","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19001","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"A5CJZAB4Z6RL","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"A5CJZAB4Z6RLUDXX","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"A5CJZAB4","created_at":"2026-07-05T08:14:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:A5CJZAB4Z6RLUDXXDO6DSR4LYS","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-30T12:58:39Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"title_canon_sha256":"93a8bf38a9337355132506131293702559ba0ad5842740f79c3a55e1164df554","abstract_canon_sha256":"89ac4fa4106ed3ee9d7c4dc7059c5dae8530f507f5df819adbdb6c7d1150dafa"},"schema_version":"1.0"},"canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:17.803296Z","signature_b64":"V8N5cIKIq1jdvx0bDsPidKco1LaCWkcNoU395XCRoG0k+KbLwkULEkcp2u9zIjZeJXQfh5A7FWVdgFzHSDUHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","last_reissued_at":"2026-07-05T08:14:17.802842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:17.802842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19001","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVHCil23AsB3vUtngBzhW7yuM7xPs97LR0LJuYUZ/JyaOJY8fxnpiqWTZA3RzGKHTBkpaVDAoDaXAx7c9djGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:04:40.662286Z"},"content_sha256":"eeb4ef798bdb1215f32ab648c5146ac781d50114a743c0222650af40471cf2dc","schema_version":"1.0","event_id":"sha256:eeb4ef798bdb1215f32ab648c5146ac781d50114a743c0222650af40471cf2dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:A5CJZAB4Z6RLUDXXDO6DSR4LYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High-probability sample complexities for policy evaluation with linear function approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alessandro Rinaldo, Cong Ma, Gen Li, Weichen Wu, Yuejie Chi, Yuting Wei","submitted_at":"2023-05-30T12:58:39Z","abstract_excerpt":"This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms: the temporal difference (TD) learning algorithm and the two-timescale linear TD with gradient correction (TDC) algorithm. In both the on-policy setting, where observations are generated from the target policy, and the off-policy setting, where samples are drawn from a beh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19001","kind":"arxiv","version":2},"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/2305.19001/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":"2026-07-05T08:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErvwNlr6pqM2e0/CQkjRevruPAkCYDNG4iP/CU4FPQ9iRyKzgsy2BJf4W7FKema6EP1ARjC++f1kYf4roJeCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:04:40.662851Z"},"content_sha256":"2280a61a9c6d35e2397baae11db33a4c6e7b87cc55ee283fa433ea71bfe0ef2e","schema_version":"1.0","event_id":"sha256:2280a61a9c6d35e2397baae11db33a4c6e7b87cc55ee283fa433ea71bfe0ef2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/bundle.json","state_url":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/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":"2026-08-10T11:04:40Z","links":{"resolver":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS","bundle":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/bundle.json","state":"https://pith.science/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5CJZAB4Z6RLUDXXDO6DSR4LYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A5CJZAB4Z6RLUDXXDO6DSR4LYS","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":"89ac4fa4106ed3ee9d7c4dc7059c5dae8530f507f5df819adbdb6c7d1150dafa","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-30T12:58:39Z","title_canon_sha256":"93a8bf38a9337355132506131293702559ba0ad5842740f79c3a55e1164df554"},"schema_version":"1.0","source":{"id":"2305.19001","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19001","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19001v2","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19001","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"A5CJZAB4Z6RL","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"A5CJZAB4Z6RLUDXX","created_at":"2026-07-05T08:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"A5CJZAB4","created_at":"2026-07-05T08:14:17Z"}],"graph_snapshots":[{"event_id":"sha256:2280a61a9c6d35e2397baae11db33a4c6e7b87cc55ee283fa433ea71bfe0ef2e","target":"graph","created_at":"2026-07-05T08:14:17Z","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/2305.19001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms: the temporal difference (TD) learning algorithm and the two-timescale linear TD with gradient correction (TDC) algorithm. In both the on-policy setting, where observations are generated from the target policy, and the off-policy setting, where samples are drawn from a beh","authors_text":"Alessandro Rinaldo, Cong Ma, Gen Li, Weichen Wu, Yuejie Chi, Yuting Wei","cross_cats":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-30T12:58:39Z","title":"High-probability sample complexities for policy evaluation with linear function approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19001","kind":"arxiv","version":2},"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:eeb4ef798bdb1215f32ab648c5146ac781d50114a743c0222650af40471cf2dc","target":"record","created_at":"2026-07-05T08:14:17Z","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":"89ac4fa4106ed3ee9d7c4dc7059c5dae8530f507f5df819adbdb6c7d1150dafa","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-30T12:58:39Z","title_canon_sha256":"93a8bf38a9337355132506131293702559ba0ad5842740f79c3a55e1164df554"},"schema_version":"1.0","source":{"id":"2305.19001","kind":"arxiv","version":2}},"canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07449c803ccfa2ba0ef71bbc39478bc48e239535eca13bd8e380892b43fa661c","first_computed_at":"2026-07-05T08:14:17.802842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:17.802842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8N5cIKIq1jdvx0bDsPidKco1LaCWkcNoU395XCRoG0k+KbLwkULEkcp2u9zIjZeJXQfh5A7FWVdgFzHSDUHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:17.803296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19001","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb4ef798bdb1215f32ab648c5146ac781d50114a743c0222650af40471cf2dc","sha256:2280a61a9c6d35e2397baae11db33a4c6e7b87cc55ee283fa433ea71bfe0ef2e"],"state_sha256":"9c77986e36809dda393d4e7ed1a98b4abb2af7ec09e61eadcc52749fff50f22f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFTRXfT24Jq1lTyJQFu7oIzO1NxjmjVF//JLVr/jeYHuDP5IDFO/PrC9yFsBpD/HQ+QMbvdKWyZObcV2xsboCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:04:40.671133Z","bundle_sha256":"1722aaa85a1b5b96b66db2a219cc5593cb7a6af7b42cbd036bbfa63a9c9c97c3"}}