{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5OTYYFYGJJKCCBEDVIUOCLI5SA","short_pith_number":"pith:5OTYYFYG","schema_version":"1.0","canonical_sha256":"eba78c17064a54210483aa28e12d1d901a32333f37570c600fee620fde72de3e","source":{"kind":"arxiv","id":"2406.01386","version":3},"attestation_state":"computed","paper":{"title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han Zhong, Jinhang Zuo, John C.S. Lui, Mohammad Hajiesmaili, Shuai Li, Siwei Wang, Wei Chen, Xuchuang Wang, Xutong Liu, Zhiyong Wang","submitted_at":"2024-06-03T14:48:53Z","abstract_excerpt":"We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process. Compared with existing CMAB works, CMAB-MT not only enhances the modeling power but also allows improved results by leveraging distinct statistical properties for multivariant random variables. For CMAB-MT, we propose a general 1-norm multivariant and triggering probability-modulated smoothness condition, and an optim"},"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":"2406.01386","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T14:48:53Z","cross_cats_sorted":[],"title_canon_sha256":"132bef75924e59c6aa335be6691aae95702a98cbd8c4cea5528871dcd1c0fcfe","abstract_canon_sha256":"e1603a24b559b98ce0b8a75fc9d7b104131aa5664691fce08bde4559af0efb50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:37.057205Z","signature_b64":"ticxgnePGLrsATF9Tunua7ccs06UiOwpnXJ0NmG1YMvxKFmBYdc9z2f2Q/zbKQrY5Cexx75SmRQMPX2i6tCgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eba78c17064a54210483aa28e12d1d901a32333f37570c600fee620fde72de3e","last_reissued_at":"2026-07-05T10:52:37.056658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:37.056658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Han Zhong, Jinhang Zuo, John C.S. Lui, Mohammad Hajiesmaili, Shuai Li, Siwei Wang, Wei Chen, Xuchuang Wang, Xutong Liu, Zhiyong Wang","submitted_at":"2024-06-03T14:48:53Z","abstract_excerpt":"We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process. Compared with existing CMAB works, CMAB-MT not only enhances the modeling power but also allows improved results by leveraging distinct statistical properties for multivariant random variables. For CMAB-MT, we propose a general 1-norm multivariant and triggering probability-modulated smoothness condition, and an optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01386","kind":"arxiv","version":3},"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/2406.01386/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":"2406.01386","created_at":"2026-07-05T10:52:37.056726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01386v3","created_at":"2026-07-05T10:52:37.056726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01386","created_at":"2026-07-05T10:52:37.056726+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OTYYFYGJJKC","created_at":"2026-07-05T10:52:37.056726+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OTYYFYGJJKCCBED","created_at":"2026-07-05T10:52:37.056726+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OTYYFYG","created_at":"2026-07-05T10:52:37.056726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04594","citing_title":"Intelligent Channel Allocation for IEEE 802.11be Multi-Link Operation: When MAB Meets LLM","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA","json":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA.json","graph_json":"https://pith.science/api/pith-number/5OTYYFYGJJKCCBEDVIUOCLI5SA/graph.json","events_json":"https://pith.science/api/pith-number/5OTYYFYGJJKCCBEDVIUOCLI5SA/events.json","paper":"https://pith.science/paper/5OTYYFYG"},"agent_actions":{"view_html":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA","download_json":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA.json","view_paper":"https://pith.science/paper/5OTYYFYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01386&json=true","fetch_graph":"https://pith.science/api/pith-number/5OTYYFYGJJKCCBEDVIUOCLI5SA/graph.json","fetch_events":"https://pith.science/api/pith-number/5OTYYFYGJJKCCBEDVIUOCLI5SA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA/action/storage_attestation","attest_author":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA/action/author_attestation","sign_citation":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA/action/citation_signature","submit_replication":"https://pith.science/pith/5OTYYFYGJJKCCBEDVIUOCLI5SA/action/replication_record"}},"created_at":"2026-07-05T10:52:37.056726+00:00","updated_at":"2026-07-05T10:52:37.056726+00:00"}