{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VBLAB5KGFSKPEQIQZMBSSKWHQH","short_pith_number":"pith:VBLAB5KG","schema_version":"1.0","canonical_sha256":"a85600f5462c94f24110cb03292ac781c7a32525d4b33fff7e4bb405c54a4d71","source":{"kind":"arxiv","id":"2406.07992","version":1},"attestation_state":"computed","paper":{"title":"A Federated Online Restless Bandit Framework for Cooperative Resource Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Jingwen Tong, Jun Zhang, Khaled B. Letaief, Liqun Fu, Xinran Li","submitted_at":"2024-06-12T08:34:53Z","abstract_excerpt":"Restless multi-armed bandits (RMABs) have been widely utilized to address resource allocation problems with Markov reward processes (MRPs). Existing works often assume that the dynamics of MRPs are known prior, which makes the RMAB problem solvable from an optimization perspective. Nevertheless, an efficient learning-based solution for RMABs with unknown system dynamics remains an open problem. In this paper, we study the cooperative resource allocation problem with unknown system dynamics of MRPs. This problem can be modeled as a multi-agent online RMAB problem, where multiple agents collabor"},"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":"2406.07992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T08:34:53Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"bf727935a599b3f9a4451639d777ac3ac29841de2969f22c41cfba5603e69969","abstract_canon_sha256":"0150a46fa1fbc7e035a05b4462d0a69e3c57943987131657aae76cab434f7f48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:41.976800Z","signature_b64":"7vVftvKqlgC1TFW+3v+X0Gju85UaKHwlAm0t34zdu1gp4vYYT38yDBRGM9SEuuDBYbW1fs5Ekc4wQtkn+CGkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a85600f5462c94f24110cb03292ac781c7a32525d4b33fff7e4bb405c54a4d71","last_reissued_at":"2026-07-05T08:30:41.976327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:41.976327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Federated Online Restless Bandit Framework for Cooperative Resource Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Jingwen Tong, Jun Zhang, Khaled B. Letaief, Liqun Fu, Xinran Li","submitted_at":"2024-06-12T08:34:53Z","abstract_excerpt":"Restless multi-armed bandits (RMABs) have been widely utilized to address resource allocation problems with Markov reward processes (MRPs). Existing works often assume that the dynamics of MRPs are known prior, which makes the RMAB problem solvable from an optimization perspective. Nevertheless, an efficient learning-based solution for RMABs with unknown system dynamics remains an open problem. In this paper, we study the cooperative resource allocation problem with unknown system dynamics of MRPs. This problem can be modeled as a multi-agent online RMAB problem, where multiple agents collabor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07992","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/2406.07992/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":"2406.07992","created_at":"2026-07-05T08:30:41.976392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07992v1","created_at":"2026-07-05T08:30:41.976392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07992","created_at":"2026-07-05T08:30:41.976392+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBLAB5KGFSKP","created_at":"2026-07-05T08:30:41.976392+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBLAB5KGFSKPEQIQ","created_at":"2026-07-05T08:30:41.976392+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBLAB5KG","created_at":"2026-07-05T08:30:41.976392+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/VBLAB5KGFSKPEQIQZMBSSKWHQH","json":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH.json","graph_json":"https://pith.science/api/pith-number/VBLAB5KGFSKPEQIQZMBSSKWHQH/graph.json","events_json":"https://pith.science/api/pith-number/VBLAB5KGFSKPEQIQZMBSSKWHQH/events.json","paper":"https://pith.science/paper/VBLAB5KG"},"agent_actions":{"view_html":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH","download_json":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH.json","view_paper":"https://pith.science/paper/VBLAB5KG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07992&json=true","fetch_graph":"https://pith.science/api/pith-number/VBLAB5KGFSKPEQIQZMBSSKWHQH/graph.json","fetch_events":"https://pith.science/api/pith-number/VBLAB5KGFSKPEQIQZMBSSKWHQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH/action/storage_attestation","attest_author":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH/action/author_attestation","sign_citation":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH/action/citation_signature","submit_replication":"https://pith.science/pith/VBLAB5KGFSKPEQIQZMBSSKWHQH/action/replication_record"}},"created_at":"2026-07-05T08:30:41.976392+00:00","updated_at":"2026-07-05T08:30:41.976392+00:00"}