{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I5KD3U3HR2BYVWI5ZYWCT5YDHU","short_pith_number":"pith:I5KD3U3H","canonical_record":{"source":{"id":"2410.16106","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T15:34:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e30896fa3995d0630d9ea3ea17dfc86d559accdba3855f37727996bb818b6154","abstract_canon_sha256":"a24b7e7430209391d4f3407d6166eee923d338f8975fbaf12ef69a387cff8a82"},"schema_version":"1.0"},"canonical_sha256":"47543dd3678e838ad91dce2c29f7033d2cb0b91eb072b5ae50597d29af4221eb","source":{"kind":"arxiv","id":"2410.16106","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16106","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16106v6","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16106","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"I5KD3U3HR2BY","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"I5KD3U3HR2BYVWI5","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"I5KD3U3H","created_at":"2026-06-23T02:13:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I5KD3U3HR2BYVWI5ZYWCT5YDHU","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16106","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T15:34:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e30896fa3995d0630d9ea3ea17dfc86d559accdba3855f37727996bb818b6154","abstract_canon_sha256":"a24b7e7430209391d4f3407d6166eee923d338f8975fbaf12ef69a387cff8a82"},"schema_version":"1.0"},"canonical_sha256":"47543dd3678e838ad91dce2c29f7033d2cb0b91eb072b5ae50597d29af4221eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:13.306308Z","signature_b64":"b12iuToe6l5w8l4Q+Z9xkypMTSIyl0kjRH7mKGgxG0Rvg6uXXTe7/CcXdwzbeVIsZH4GPUzwcZnTSLdahcQRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47543dd3678e838ad91dce2c29f7033d2cb0b91eb072b5ae50597d29af4221eb","last_reissued_at":"2026-06-23T02:13:13.305856Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:13.305856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16106","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yyWMTXmkwoOCcYpSJQQxd8kcnotmYUQz2yCAwiW7eMzSDILcJaiIpqYjcJRq3GTJbDtasst6QRTjV8Cn1UNxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:40:46.061515Z"},"content_sha256":"cb767a565cbcc2228dfc57f49064a8f519551fe1cc1c9bee3245cc3e8b790a99","schema_version":"1.0","event_id":"sha256:cb767a565cbcc2228dfc57f49064a8f519551fe1cc1c9bee3245cc3e8b790a99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I5KD3U3HR2BYVWI5ZYWCT5YDHU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical Inference for Policy Evaluation with Temporal Difference Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Rinaldo, Gen Li, Weichen Wu, Yuting Wei","submitted_at":"2024-10-21T15:34:44Z","abstract_excerpt":"We investigate the statistical properties of Temporal Difference (TD) learning with Polyak-Ruppert averaging, arguably one of the most widely used algorithms in reinforcement learning, for the task of estimating the parameters of the optimal linear approximation to the value function. Assuming independent samples, we make three theoretical contributions that improve upon the current state-of-the-art results: (i) we establish refined high-dimensional Berry-Esseen bounds over the class of convex sets, achieving faster rates than the best known results, and (ii) we propose and analyze a novel, co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16106","kind":"arxiv","version":6},"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/2410.16106/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":"2026-06-23T02:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UG+0YnKiv4QtzUUgr6d0OXw+oOA+lfC3SklVvY64Qmh4YqBgQyWiqQYT9Y0t5YzPawo9b78TbfpE9xFNjxbmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:40:46.062236Z"},"content_sha256":"c2ac7f5322697f9fd15ba732ac017a1fd9440f08957c6b1cbccfdbc57616618a","schema_version":"1.0","event_id":"sha256:c2ac7f5322697f9fd15ba732ac017a1fd9440f08957c6b1cbccfdbc57616618a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU/bundle.json","state_url":"https://pith.science/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU/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":"2026-08-17T07:40:46Z","links":{"resolver":"https://pith.science/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU","bundle":"https://pith.science/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU/bundle.json","state":"https://pith.science/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5KD3U3HR2BYVWI5ZYWCT5YDHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I5KD3U3HR2BYVWI5ZYWCT5YDHU","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":"a24b7e7430209391d4f3407d6166eee923d338f8975fbaf12ef69a387cff8a82","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T15:34:44Z","title_canon_sha256":"e30896fa3995d0630d9ea3ea17dfc86d559accdba3855f37727996bb818b6154"},"schema_version":"1.0","source":{"id":"2410.16106","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16106","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16106v6","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16106","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"I5KD3U3HR2BY","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"I5KD3U3HR2BYVWI5","created_at":"2026-06-23T02:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"I5KD3U3H","created_at":"2026-06-23T02:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:c2ac7f5322697f9fd15ba732ac017a1fd9440f08957c6b1cbccfdbc57616618a","target":"graph","created_at":"2026-06-23T02:13:13Z","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/2410.16106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the statistical properties of Temporal Difference (TD) learning with Polyak-Ruppert averaging, arguably one of the most widely used algorithms in reinforcement learning, for the task of estimating the parameters of the optimal linear approximation to the value function. Assuming independent samples, we make three theoretical contributions that improve upon the current state-of-the-art results: (i) we establish refined high-dimensional Berry-Esseen bounds over the class of convex sets, achieving faster rates than the best known results, and (ii) we propose and analyze a novel, co","authors_text":"Alessandro Rinaldo, Gen Li, Weichen Wu, Yuting Wei","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T15:34:44Z","title":"Statistical Inference for Policy Evaluation with Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16106","kind":"arxiv","version":6},"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:cb767a565cbcc2228dfc57f49064a8f519551fe1cc1c9bee3245cc3e8b790a99","target":"record","created_at":"2026-06-23T02:13:13Z","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":"a24b7e7430209391d4f3407d6166eee923d338f8975fbaf12ef69a387cff8a82","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T15:34:44Z","title_canon_sha256":"e30896fa3995d0630d9ea3ea17dfc86d559accdba3855f37727996bb818b6154"},"schema_version":"1.0","source":{"id":"2410.16106","kind":"arxiv","version":6}},"canonical_sha256":"47543dd3678e838ad91dce2c29f7033d2cb0b91eb072b5ae50597d29af4221eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47543dd3678e838ad91dce2c29f7033d2cb0b91eb072b5ae50597d29af4221eb","first_computed_at":"2026-06-23T02:13:13.305856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:13.305856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b12iuToe6l5w8l4Q+Z9xkypMTSIyl0kjRH7mKGgxG0Rvg6uXXTe7/CcXdwzbeVIsZH4GPUzwcZnTSLdahcQRCw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:13.306308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16106","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb767a565cbcc2228dfc57f49064a8f519551fe1cc1c9bee3245cc3e8b790a99","sha256:c2ac7f5322697f9fd15ba732ac017a1fd9440f08957c6b1cbccfdbc57616618a"],"state_sha256":"46a3a616f29a9ba4c6f69da2ea8ab0845df594450f15efd5f2de4dec25b44c5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zEvAttLWapYfW72zHZzo5KfI9eJFk1PGILcPa+Ml6uZL95otQzObKTtxw6egv/puCTljfueDMJ0sLSt799HxDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:40:46.075686Z","bundle_sha256":"4c06d297b51677a834597cf9186102db3ec01f5100b6f6c2a6c2e99cfba8c528"}}