{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DOMSK7LWA5XQ7ORNASTEKXUW3B","short_pith_number":"pith:DOMSK7LW","schema_version":"1.0","canonical_sha256":"1b99257d76076f0fba2d04a6455e96d862d40be9b0bb7af6a0fb0bc4734deba2","source":{"kind":"arxiv","id":"2608.06545","version":1},"attestation_state":"computed","paper":{"title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuejie Chi, Yuepeng Yang, Yuxin Chen","submitted_at":"2026-08-06T19:49:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.06545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T19:49:48Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"842c38078a4f6c07b4dfb0b255ce49fa8ed8c96170a3128b5a1af0af6ad8bdcb","abstract_canon_sha256":"50de4cdf4d716dece9921c231c1fa472bc6f364dfd0bdb0f9fb9860132f8eac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:11:13.997013Z","signature_b64":"dCS8R8iqY7eBccEWnJYuRbMqUBfwWcxyYFjQIFERfyr797TTJ6W+kgkB5HAK25d5e3+1fKxVOKS5pBNM/UT7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b99257d76076f0fba2d04a6455e96d862d40be9b0bb7af6a0fb0bc4734deba2","last_reissued_at":"2026-08-10T01:11:13.994700Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:11:13.994700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuejie Chi, Yuepeng Yang, Yuxin Chen","submitted_at":"2026-08-06T19:49:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06545","kind":"arxiv","version":1},"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/2608.06545/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.06545","created_at":"2026-08-10T01:11:13.995580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06545v1","created_at":"2026-08-10T01:11:13.995580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06545","created_at":"2026-08-10T01:11:13.995580+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOMSK7LWA5XQ","created_at":"2026-08-10T01:11:13.995580+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOMSK7LWA5XQ7ORN","created_at":"2026-08-10T01:11:13.995580+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOMSK7LW","created_at":"2026-08-10T01:11:13.995580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B","json":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B.json","graph_json":"https://pith.science/api/pith-number/DOMSK7LWA5XQ7ORNASTEKXUW3B/graph.json","events_json":"https://pith.science/api/pith-number/DOMSK7LWA5XQ7ORNASTEKXUW3B/events.json","paper":"https://pith.science/paper/DOMSK7LW"},"agent_actions":{"view_html":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B","download_json":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B.json","view_paper":"https://pith.science/paper/DOMSK7LW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06545&json=true","fetch_graph":"https://pith.science/api/pith-number/DOMSK7LWA5XQ7ORNASTEKXUW3B/graph.json","fetch_events":"https://pith.science/api/pith-number/DOMSK7LWA5XQ7ORNASTEKXUW3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B/action/storage_attestation","attest_author":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B/action/author_attestation","sign_citation":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B/action/citation_signature","submit_replication":"https://pith.science/pith/DOMSK7LWA5XQ7ORNASTEKXUW3B/action/replication_record"}},"created_at":"2026-08-10T01:11:13.995580+00:00","updated_at":"2026-08-10T01:11:13.995580+00:00"}