{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OINPF2C4AHZ7QKFHTL4GXDNWJV","short_pith_number":"pith:OINPF2C4","schema_version":"1.0","canonical_sha256":"721af2e85c01f3f828a79af86b8db64d47647571c6a0298c6d7c4066eedfebea","source":{"kind":"arxiv","id":"2110.15771","version":4},"attestation_state":"computed","paper":{"title":"Collaborative Pure Exploration in Kernel Bandit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Longbo Huang, Wei Chen, Yihan Du, Yuko Kuroki","submitted_at":"2021-10-29T13:39:14Z","abstract_excerpt":"In this paper, we formulate a Collaborative Pure Exploration in Kernel Bandit problem (CoPE-KB), which provides a novel model for multi-agent multi-task decision making under limited communication and general reward functions, and is applicable to many online learning tasks, e.g., recommendation systems and network scheduling. We consider two settings of CoPE-KB, i.e., Fixed-Confidence (FC) and Fixed-Budget (FB), and design two optimal algorithms CoopKernelFC (for FC) and CoopKernelFB (for FB). Our algorithms are equipped with innovative and efficient kernelized estimators to simultaneously ac"},"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":"2110.15771","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T13:39:14Z","cross_cats_sorted":[],"title_canon_sha256":"39671b02f0cc7bfc30ab5f46553fe99520efc041924de4604ffb8dd7db132298","abstract_canon_sha256":"2f030fb69ad8e9e2a40eb8db266ca149af8a2fb1e75e5fcead49c6d89e84d5b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:38.728779Z","signature_b64":"7zLEWSh1W94RZuJO4BcG5lOIUeu9qN2JlIyJmYLuEpIGqh2oOmKlk/NbL+SfYC3qdNx6GdlVsEA9jcn3XWcgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"721af2e85c01f3f828a79af86b8db64d47647571c6a0298c6d7c4066eedfebea","last_reissued_at":"2026-07-05T05:51:38.728305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:38.728305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Pure Exploration in Kernel Bandit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Longbo Huang, Wei Chen, Yihan Du, Yuko Kuroki","submitted_at":"2021-10-29T13:39:14Z","abstract_excerpt":"In this paper, we formulate a Collaborative Pure Exploration in Kernel Bandit problem (CoPE-KB), which provides a novel model for multi-agent multi-task decision making under limited communication and general reward functions, and is applicable to many online learning tasks, e.g., recommendation systems and network scheduling. We consider two settings of CoPE-KB, i.e., Fixed-Confidence (FC) and Fixed-Budget (FB), and design two optimal algorithms CoopKernelFC (for FC) and CoopKernelFB (for FB). Our algorithms are equipped with innovative and efficient kernelized estimators to simultaneously ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15771","kind":"arxiv","version":4},"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/2110.15771/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":"2110.15771","created_at":"2026-07-05T05:51:38.728378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15771v4","created_at":"2026-07-05T05:51:38.728378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15771","created_at":"2026-07-05T05:51:38.728378+00:00"},{"alias_kind":"pith_short_12","alias_value":"OINPF2C4AHZ7","created_at":"2026-07-05T05:51:38.728378+00:00"},{"alias_kind":"pith_short_16","alias_value":"OINPF2C4AHZ7QKFH","created_at":"2026-07-05T05:51:38.728378+00:00"},{"alias_kind":"pith_short_8","alias_value":"OINPF2C4","created_at":"2026-07-05T05:51:38.728378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13690","citing_title":"Multi-Agent Best Arm Identification in Stochastic Linear Bandits","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV","json":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV.json","graph_json":"https://pith.science/api/pith-number/OINPF2C4AHZ7QKFHTL4GXDNWJV/graph.json","events_json":"https://pith.science/api/pith-number/OINPF2C4AHZ7QKFHTL4GXDNWJV/events.json","paper":"https://pith.science/paper/OINPF2C4"},"agent_actions":{"view_html":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV","download_json":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV.json","view_paper":"https://pith.science/paper/OINPF2C4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15771&json=true","fetch_graph":"https://pith.science/api/pith-number/OINPF2C4AHZ7QKFHTL4GXDNWJV/graph.json","fetch_events":"https://pith.science/api/pith-number/OINPF2C4AHZ7QKFHTL4GXDNWJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV/action/storage_attestation","attest_author":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV/action/author_attestation","sign_citation":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV/action/citation_signature","submit_replication":"https://pith.science/pith/OINPF2C4AHZ7QKFHTL4GXDNWJV/action/replication_record"}},"created_at":"2026-07-05T05:51:38.728378+00:00","updated_at":"2026-07-05T05:51:38.728378+00:00"}