{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OXIFCPU27LPQHLWNFTTGZAEKJ2","short_pith_number":"pith:OXIFCPU2","canonical_record":{"source":{"id":"2310.14286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-22T12:37:25Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"c6cb245a3b3d86f3dcf9711cb075efb837355a2d6c452318e326fc893b782038","abstract_canon_sha256":"2cfc0a38ed1ffc14ab4d5eac768242be951d760cbf624ba205aab2cf871f9051"},"schema_version":"1.0"},"canonical_sha256":"75d0513e9afadf03aecd2ce66c808a4ea606b508c17ecdd6355b7382adf2d2e8","source":{"kind":"arxiv","id":"2310.14286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14286","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14286v2","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14286","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"OXIFCPU27LPQ","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"OXIFCPU27LPQHLWN","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"OXIFCPU2","created_at":"2026-07-05T08:32:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OXIFCPU27LPQHLWNFTTGZAEKJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-22T12:37:25Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"c6cb245a3b3d86f3dcf9711cb075efb837355a2d6c452318e326fc893b782038","abstract_canon_sha256":"2cfc0a38ed1ffc14ab4d5eac768242be951d760cbf624ba205aab2cf871f9051"},"schema_version":"1.0"},"canonical_sha256":"75d0513e9afadf03aecd2ce66c808a4ea606b508c17ecdd6355b7382adf2d2e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:09.585763Z","signature_b64":"A6T/hhrUcv1yo7KKd8kq+LAUZ28eI6ZpQmqlTenJH8z23xeRKLoH/+C6t+Zl+tms8qRkJvzNOwZOO8TSoGg7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d0513e9afadf03aecd2ce66c808a4ea606b508c17ecdd6355b7382adf2d2e8","last_reissued_at":"2026-07-05T08:32:09.585240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:09.585240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14286","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":"2026-07-05T08:32:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zUs9AfmPyxaeNv+ww2+iqTdvIpM8IWrTpRm/quxXVzNMm6lnRPcuYGi9ixPzSHYAyk09XCU7uglcAw8DtgDiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:37:27.425253Z"},"content_sha256":"79df2815fc7e1460cc3b26872166f69e3f5a8fe861c3e728bd407a1f80a31b92","schema_version":"1.0","event_id":"sha256:79df2815fc7e1460cc3b26872166f69e3f5a8fe861c3e728bd407a1f80a31b92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OXIFCPU27LPQHLWNFTTGZAEKJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Daniil Tiapkin, Eric Moulines, Sergey Samsonov","submitted_at":"2023-10-22T12:37:25Z","abstract_excerpt":"In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple algorithm with a universal and instance-independent step size together with Polyak-Ruppert tail averaging is sufficient to obtain near-optimal variance and bias terms. We also provide the respective sample complexity bounds. Our proof technique is based on refined error bounds for linear stochastic approximation together with the novel stability result for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14286","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/2310.14286/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":"2026-07-05T08:32:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5vKjBTlZoTw14UEUgTk8AHsBPWnm9VfGiA9A9aRquDED3sQHnCZcx3fM/wbXqmGi4Jzvpmigfg77RVywhu8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:37:27.425800Z"},"content_sha256":"d4a95b3eed17051157edeb9c26d2cc3c06ae48c719fe411db001bb5fbc6233a9","schema_version":"1.0","event_id":"sha256:d4a95b3eed17051157edeb9c26d2cc3c06ae48c719fe411db001bb5fbc6233a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2/bundle.json","state_url":"https://pith.science/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2/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":"2026-08-04T11:37:27Z","links":{"resolver":"https://pith.science/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2","bundle":"https://pith.science/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2/bundle.json","state":"https://pith.science/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXIFCPU27LPQHLWNFTTGZAEKJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OXIFCPU27LPQHLWNFTTGZAEKJ2","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":"2cfc0a38ed1ffc14ab4d5eac768242be951d760cbf624ba205aab2cf871f9051","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-22T12:37:25Z","title_canon_sha256":"c6cb245a3b3d86f3dcf9711cb075efb837355a2d6c452318e326fc893b782038"},"schema_version":"1.0","source":{"id":"2310.14286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14286","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14286v2","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14286","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"OXIFCPU27LPQ","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"OXIFCPU27LPQHLWN","created_at":"2026-07-05T08:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"OXIFCPU2","created_at":"2026-07-05T08:32:09Z"}],"graph_snapshots":[{"event_id":"sha256:d4a95b3eed17051157edeb9c26d2cc3c06ae48c719fe411db001bb5fbc6233a9","target":"graph","created_at":"2026-07-05T08:32:09Z","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/2310.14286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple algorithm with a universal and instance-independent step size together with Polyak-Ruppert tail averaging is sufficient to obtain near-optimal variance and bias terms. We also provide the respective sample complexity bounds. Our proof technique is based on refined error bounds for linear stochastic approximation together with the novel stability result for t","authors_text":"Alexey Naumov, Daniil Tiapkin, Eric Moulines, Sergey Samsonov","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-22T12:37:25Z","title":"Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14286","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":"sha256:79df2815fc7e1460cc3b26872166f69e3f5a8fe861c3e728bd407a1f80a31b92","target":"record","created_at":"2026-07-05T08:32:09Z","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":"2cfc0a38ed1ffc14ab4d5eac768242be951d760cbf624ba205aab2cf871f9051","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-22T12:37:25Z","title_canon_sha256":"c6cb245a3b3d86f3dcf9711cb075efb837355a2d6c452318e326fc893b782038"},"schema_version":"1.0","source":{"id":"2310.14286","kind":"arxiv","version":2}},"canonical_sha256":"75d0513e9afadf03aecd2ce66c808a4ea606b508c17ecdd6355b7382adf2d2e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75d0513e9afadf03aecd2ce66c808a4ea606b508c17ecdd6355b7382adf2d2e8","first_computed_at":"2026-07-05T08:32:09.585240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:09.585240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A6T/hhrUcv1yo7KKd8kq+LAUZ28eI6ZpQmqlTenJH8z23xeRKLoH/+C6t+Zl+tms8qRkJvzNOwZOO8TSoGg7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:09.585763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79df2815fc7e1460cc3b26872166f69e3f5a8fe861c3e728bd407a1f80a31b92","sha256:d4a95b3eed17051157edeb9c26d2cc3c06ae48c719fe411db001bb5fbc6233a9"],"state_sha256":"18276e77acb0308201ae5bf5b994bbe0558bbd94c7f5d38e0d7d56a7f300e69d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wz5aZCWTRXlIGoKYn82jgAppJBGtPnpWUctu38omI87GXKdXysvByxIP8KgHeLCfF3UZIFCnGzQqsymayyP8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:37:27.439603Z","bundle_sha256":"8f4682ee33927e554cd634f0793f4c00ffa19f77560dd57a7e8d08a30e90e6ae"}}