{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J5YDRWETAHAX4WKTC3QQVCVVWT","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":"c3b15b1aa3cb3036118440991d2b7541cdac1fcb34bf3f9b2506a44453844d23","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-20T00:53:22Z","title_canon_sha256":"3d7d8da93cb5cbf28b282603e08d529885da93d9afa3069d4bc4d9cca5f35be9"},"schema_version":"1.0","source":{"id":"2502.14172","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14172","created_at":"2026-07-05T11:02:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14172v2","created_at":"2026-07-05T11:02:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14172","created_at":"2026-07-05T11:02:18Z"},{"alias_kind":"pith_short_12","alias_value":"J5YDRWETAHAX","created_at":"2026-07-05T11:02:18Z"},{"alias_kind":"pith_short_16","alias_value":"J5YDRWETAHAX4WKT","created_at":"2026-07-05T11:02:18Z"},{"alias_kind":"pith_short_8","alias_value":"J5YDRWET","created_at":"2026-07-05T11:02:18Z"}],"graph_snapshots":[{"event_id":"sha256:f3ce041fc7162c59eb1d9e4130b57a27d130b612172a378b780de286f4568ff1","target":"graph","created_at":"2026-07-05T11:02:18Z","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/2502.14172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy {\\pi}. Previous works on statistical analysis of distributional TD learning mainly focus on the tabular case. In contrast, we first consider the linear function approximation setting and derive sharp finite-sample rates. Our theoretical results demonstrate that the sample complexity of linear distributional TD lear","authors_text":"Kaicheng Jin, Liangyu Zhang, Yang Peng, Zhihua Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-20T00:53:22Z","title":"A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14172","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":"sha256:5bd7a678f6db398d4006583bd3bca1c7629e74e95f7d606472a0fd759884146a","target":"record","created_at":"2026-07-05T11:02:18Z","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":"c3b15b1aa3cb3036118440991d2b7541cdac1fcb34bf3f9b2506a44453844d23","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-20T00:53:22Z","title_canon_sha256":"3d7d8da93cb5cbf28b282603e08d529885da93d9afa3069d4bc4d9cca5f35be9"},"schema_version":"1.0","source":{"id":"2502.14172","kind":"arxiv","version":2}},"canonical_sha256":"4f7038d89301c17e595316e10a8ab5b4db2640e14ac4e08c0a38beacb97c0f92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f7038d89301c17e595316e10a8ab5b4db2640e14ac4e08c0a38beacb97c0f92","first_computed_at":"2026-07-05T11:02:18.275262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:18.275262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MQ9rmjDQs58j9XhkrBW4o52XiayiUkHTmZ8yHtK0Qnavv66ZMa65clPEPWgS61MXjUyh3m/P2pTxFiH44ONADg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:18.275775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14172","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bd7a678f6db398d4006583bd3bca1c7629e74e95f7d606472a0fd759884146a","sha256:f3ce041fc7162c59eb1d9e4130b57a27d130b612172a378b780de286f4568ff1"],"state_sha256":"daa3e1b8bb1786a4055a925758d67bcdeae50c4069f68d669eed4afb47b08f40"}