{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5K4UQRFBMON5OM6LL44S2LFQEB","short_pith_number":"pith:5K4UQRFB","schema_version":"1.0","canonical_sha256":"eab94844a1639bd733cb5f392d2cb02041ea64120124e351e7813e6cc1b43aa4","source":{"kind":"arxiv","id":"2401.09073","version":1},"attestation_state":"computed","paper":{"title":"Fixed-Budget Differentially Private Best Arm Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"P. N. Karthik, Vincent Y. F. Tan, Yeow Meng Chee, Zhirui Chen","submitted_at":"2024-01-17T09:23:25Z","abstract_excerpt":"We study best arm identification (BAI) in linear bandits in the fixed-budget regime under differential privacy constraints, when the arm rewards are supported on the unit interval. Given a finite budget $T$ and a privacy parameter $\\varepsilon>0$, the goal is to minimise the error probability in finding the arm with the largest mean after $T$ sampling rounds, subject to the constraint that the policy of the decision maker satisfies a certain {\\em $\\varepsilon$-differential privacy} ($\\varepsilon$-DP) constraint. We construct a policy satisfying the $\\varepsilon$-DP constraint (called {\\sc DP-B"},"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":"2401.09073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T09:23:25Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"6dd68f59686434989a2382e14c62cb4eb8fb87ff7cf2510b7c04453ff3d671d5","abstract_canon_sha256":"889d3543c4b82ebe274849590fad14e8a0b93a031d58c47cd56c11bb7c0d8cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:39.080171Z","signature_b64":"X/I8FR6zOcu3oPw2ZDwwAmtO5SOW4yx2GLT9UiXkN1YJUoAElwG0m3CvgM5zKpWThMkOIcKtj4BJhBaLFoEPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eab94844a1639bd733cb5f392d2cb02041ea64120124e351e7813e6cc1b43aa4","last_reissued_at":"2026-07-05T07:34:39.079757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:39.079757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixed-Budget Differentially Private Best Arm Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"P. N. Karthik, Vincent Y. F. Tan, Yeow Meng Chee, Zhirui Chen","submitted_at":"2024-01-17T09:23:25Z","abstract_excerpt":"We study best arm identification (BAI) in linear bandits in the fixed-budget regime under differential privacy constraints, when the arm rewards are supported on the unit interval. Given a finite budget $T$ and a privacy parameter $\\varepsilon>0$, the goal is to minimise the error probability in finding the arm with the largest mean after $T$ sampling rounds, subject to the constraint that the policy of the decision maker satisfies a certain {\\em $\\varepsilon$-differential privacy} ($\\varepsilon$-DP) constraint. We construct a policy satisfying the $\\varepsilon$-DP constraint (called {\\sc DP-B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09073","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/2401.09073/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":"2401.09073","created_at":"2026-07-05T07:34:39.079806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09073v1","created_at":"2026-07-05T07:34:39.079806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09073","created_at":"2026-07-05T07:34:39.079806+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K4UQRFBMON5","created_at":"2026-07-05T07:34:39.079806+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K4UQRFBMON5OM6L","created_at":"2026-07-05T07:34:39.079806+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K4UQRFB","created_at":"2026-07-05T07:34:39.079806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05175","citing_title":"Blind Targeting: Personalization under Third-Party Privacy Constraints","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB","json":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB.json","graph_json":"https://pith.science/api/pith-number/5K4UQRFBMON5OM6LL44S2LFQEB/graph.json","events_json":"https://pith.science/api/pith-number/5K4UQRFBMON5OM6LL44S2LFQEB/events.json","paper":"https://pith.science/paper/5K4UQRFB"},"agent_actions":{"view_html":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB","download_json":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB.json","view_paper":"https://pith.science/paper/5K4UQRFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09073&json=true","fetch_graph":"https://pith.science/api/pith-number/5K4UQRFBMON5OM6LL44S2LFQEB/graph.json","fetch_events":"https://pith.science/api/pith-number/5K4UQRFBMON5OM6LL44S2LFQEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB/action/storage_attestation","attest_author":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB/action/author_attestation","sign_citation":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB/action/citation_signature","submit_replication":"https://pith.science/pith/5K4UQRFBMON5OM6LL44S2LFQEB/action/replication_record"}},"created_at":"2026-07-05T07:34:39.079806+00:00","updated_at":"2026-07-05T07:34:39.079806+00:00"}