{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DHBFL4KUDR4KRUZJMKEC6XSKIT","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":"1f04b1bc7c1c70fb71a01947d41887d21be3823529765e417a929cfad82c2625","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T21:26:43Z","title_canon_sha256":"a87cd0c7ead3347423b21e8f3bf9e39d3daee3347c3d50a1a28550cac279509e"},"schema_version":"1.0","source":{"id":"2306.00196","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00196","created_at":"2026-07-05T07:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00196v3","created_at":"2026-07-05T07:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00196","created_at":"2026-07-05T07:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"DHBFL4KUDR4K","created_at":"2026-07-05T07:33:51Z"},{"alias_kind":"pith_short_16","alias_value":"DHBFL4KUDR4KRUZJ","created_at":"2026-07-05T07:33:51Z"},{"alias_kind":"pith_short_8","alias_value":"DHBFL4KU","created_at":"2026-07-05T07:33:51Z"}],"graph_snapshots":[{"event_id":"sha256:b931ad6ff739c4963c5e7a3c18171c3815ca736b451932346cc5a42ba7d29289","target":"graph","created_at":"2026-07-05T07:33:51Z","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/2306.00196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the infinite-horizon restless bandit problem with the average reward criterion, in both discrete-time and continuous-time settings. A fundamental goal is to efficiently compute policies that achieve a diminishing optimality gap as the number of arms, $N$, grows large. Existing results on asymptotic optimality all rely on the uniform global attractor property (UGAP), a complex and challenging-to-verify assumption. In this paper, we propose a general, simulation-based framework, Follow-the-Virtual-Advice, that converts any single-armed policy into a policy for the original $N$-armed pro","authors_text":"Qiaomin Xie, Weina Wang, Yige Hong, Yudong Chen","cross_cats":["math.OC","math.PR","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T21:26:43Z","title":"Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00196","kind":"arxiv","version":3},"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":"sha256:40faff5151803da05fc735b839473450442d2c7e95b86ddb355a95b3bbd848e2","target":"record","created_at":"2026-07-05T07:33:51Z","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":"1f04b1bc7c1c70fb71a01947d41887d21be3823529765e417a929cfad82c2625","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T21:26:43Z","title_canon_sha256":"a87cd0c7ead3347423b21e8f3bf9e39d3daee3347c3d50a1a28550cac279509e"},"schema_version":"1.0","source":{"id":"2306.00196","kind":"arxiv","version":3}},"canonical_sha256":"19c255f1541c78a8d32962882f5e4a44ed09bfa68f7fcdffd70f41e581d09085","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19c255f1541c78a8d32962882f5e4a44ed09bfa68f7fcdffd70f41e581d09085","first_computed_at":"2026-07-05T07:33:51.526179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:51.526179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"716x9xMwI4nxvayH1c6ti6L6xTFImXjH5S83mnPNVnupT4woeVm2VqzNMp2VbKi51LogD60l8KsD/2DDllsbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:51.526754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00196","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40faff5151803da05fc735b839473450442d2c7e95b86ddb355a95b3bbd848e2","sha256:b931ad6ff739c4963c5e7a3c18171c3815ca736b451932346cc5a42ba7d29289"],"state_sha256":"aa1e6071f8a99e05ba89e05dd3194be773238d9f059456f6621072977b264998"}