{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DOMSK7LWA5XQ7ORNASTEKXUW3B","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":"50de4cdf4d716dece9921c231c1fa472bc6f364dfd0bdb0f9fb9860132f8eac8","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T19:49:48Z","title_canon_sha256":"842c38078a4f6c07b4dfb0b255ce49fa8ed8c96170a3128b5a1af0af6ad8bdcb"},"schema_version":"1.0","source":{"id":"2608.06545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06545","created_at":"2026-08-10T01:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06545v1","created_at":"2026-08-10T01:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06545","created_at":"2026-08-10T01:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"DOMSK7LWA5XQ","created_at":"2026-08-10T01:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"DOMSK7LWA5XQ7ORN","created_at":"2026-08-10T01:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"DOMSK7LW","created_at":"2026-08-10T01:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:2f24247a4f093d92741409cb3a088f37336656f089195b798dcc9b6f05bca72d","target":"graph","created_at":"2026-08-10T01:11:13Z","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/2608.06545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty. We study how many samples are necessary and sufficient to learn an $\\varepsilon$-optimal robust policy under the average-reward criterion. A generative model provides samples from the nominal transition kernel, whereas policy performance is evaluated over $(s,a)$-rectangular total-variation uncertainty sets of radius at most $\\sigma$.\n  Let $H_0$ and $H_\\sigma$ denote the nominal and robust optimal bias spans, respectively. We identify $\\sigma H_0$ as the per","authors_text":"Yuejie Chi, Yuepeng Yang, Yuxin Chen","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T19:49:48Z","title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06545","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":"sha256:198e6e01c585a17eef2203669413c03d87c122a0b7ea886597a639b8c08cbe72","target":"record","created_at":"2026-08-10T01:11:13Z","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":"50de4cdf4d716dece9921c231c1fa472bc6f364dfd0bdb0f9fb9860132f8eac8","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T19:49:48Z","title_canon_sha256":"842c38078a4f6c07b4dfb0b255ce49fa8ed8c96170a3128b5a1af0af6ad8bdcb"},"schema_version":"1.0","source":{"id":"2608.06545","kind":"arxiv","version":1}},"canonical_sha256":"1b99257d76076f0fba2d04a6455e96d862d40be9b0bb7af6a0fb0bc4734deba2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b99257d76076f0fba2d04a6455e96d862d40be9b0bb7af6a0fb0bc4734deba2","first_computed_at":"2026-08-10T01:11:13.994700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:11:13.994700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dCS8R8iqY7eBccEWnJYuRbMqUBfwWcxyYFjQIFERfyr797TTJ6W+kgkB5HAK25d5e3+1fKxVOKS5pBNM/UT7Ag==","signature_status":"signed_v1","signed_at":"2026-08-10T01:11:13.997013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:198e6e01c585a17eef2203669413c03d87c122a0b7ea886597a639b8c08cbe72","sha256:2f24247a4f093d92741409cb3a088f37336656f089195b798dcc9b6f05bca72d"],"state_sha256":"196ca71fffbd1e3278636421ac9211cce5659a6829e4865e874ce29f69a83397"}