{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZNKFVYHFMMPQOYT6BQVZROAY7G","short_pith_number":"pith:ZNKFVYHF","schema_version":"1.0","canonical_sha256":"cb545ae0e5631f07627e0c2b98b818f9b4dbc19bc11c34878a59cd021c8bba2d","source":{"kind":"arxiv","id":"2508.10804","version":1},"attestation_state":"computed","paper":{"title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kai Wang, Ping-Chun Hsieh, Yu-Heng Hung","submitted_at":"2025-08-14T16:26:00Z","abstract_excerpt":"Online restless multi-armed bandits (RMABs) typically assume that each arm follows a stationary Markov Decision Process (MDP) with fixed state transitions and rewards. However, in real-world applications like healthcare and recommendation systems, these assumptions often break due to non-stationary dynamics, posing significant challenges for traditional RMAB algorithms. In this work, we specifically consider $N$-armd RMAB with non-stationary transition constrained by bounded variation budgets $B$. Our proposed \\rmab\\; algorithm integrates sliding window reinforcement learning (RL) with an uppe"},"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":"2508.10804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T16:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"64d6eb4fcae555f372dc5c50e53412496e84aa286286f4d59dacebfc0b0c9b3f","abstract_canon_sha256":"939b5f09885663e5e1695100191a18dcc848417fbd960b7b6471b80c5b190369"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:02.859719Z","signature_b64":"9DiJ/eUkeftabfm471ow0+vyKso1e6+OzDvtlG3ueiWGe3AruGE979C1kfCA7dJ/hsKcyXWVmfPKhiixronbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb545ae0e5631f07627e0c2b98b818f9b4dbc19bc11c34878a59cd021c8bba2d","last_reissued_at":"2026-07-05T11:54:02.859237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:02.859237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kai Wang, Ping-Chun Hsieh, Yu-Heng Hung","submitted_at":"2025-08-14T16:26:00Z","abstract_excerpt":"Online restless multi-armed bandits (RMABs) typically assume that each arm follows a stationary Markov Decision Process (MDP) with fixed state transitions and rewards. However, in real-world applications like healthcare and recommendation systems, these assumptions often break due to non-stationary dynamics, posing significant challenges for traditional RMAB algorithms. In this work, we specifically consider $N$-armd RMAB with non-stationary transition constrained by bounded variation budgets $B$. Our proposed \\rmab\\; algorithm integrates sliding window reinforcement learning (RL) with an uppe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10804","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/2508.10804/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":"2508.10804","created_at":"2026-07-05T11:54:02.859321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10804v1","created_at":"2026-07-05T11:54:02.859321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10804","created_at":"2026-07-05T11:54:02.859321+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNKFVYHFMMPQ","created_at":"2026-07-05T11:54:02.859321+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNKFVYHFMMPQOYT6","created_at":"2026-07-05T11:54:02.859321+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNKFVYHF","created_at":"2026-07-05T11:54:02.859321+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/ZNKFVYHFMMPQOYT6BQVZROAY7G","json":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G.json","graph_json":"https://pith.science/api/pith-number/ZNKFVYHFMMPQOYT6BQVZROAY7G/graph.json","events_json":"https://pith.science/api/pith-number/ZNKFVYHFMMPQOYT6BQVZROAY7G/events.json","paper":"https://pith.science/paper/ZNKFVYHF"},"agent_actions":{"view_html":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G","download_json":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G.json","view_paper":"https://pith.science/paper/ZNKFVYHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10804&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNKFVYHFMMPQOYT6BQVZROAY7G/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNKFVYHFMMPQOYT6BQVZROAY7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G/action/storage_attestation","attest_author":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G/action/author_attestation","sign_citation":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G/action/citation_signature","submit_replication":"https://pith.science/pith/ZNKFVYHFMMPQOYT6BQVZROAY7G/action/replication_record"}},"created_at":"2026-07-05T11:54:02.859321+00:00","updated_at":"2026-07-05T11:54:02.859321+00:00"}