{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LTOYAJ44K6NRB6L642HOSXRHJR","short_pith_number":"pith:LTOYAJ44","schema_version":"1.0","canonical_sha256":"5cdd80279c579b10f97ee68ee95e274c5cead6f73706453e7f9072d57b7b05d4","source":{"kind":"arxiv","id":"2405.15090","version":1},"attestation_state":"computed","paper":{"title":"Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashutosh Nayyar, Dengwang Tang, Pierluigi Nuzzo, Rahul Jain","submitted_at":"2024-05-23T22:35:11Z","abstract_excerpt":"In this paper, we introduce the constrained best mixed arm identification (CBMAI) problem with a fixed budget. This is a pure exploration problem in a stochastic finite armed bandit model. Each arm is associated with a reward and multiple types of costs from unknown distributions. Unlike the unconstrained best arm identification problem, the optimal solution for the CBMAI problem may be a randomized mixture of multiple arms. The goal thus is to find the best mixed arm that maximizes the expected reward subject to constraints on the expected costs with a given learning budget $N$. We propose a "},"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":"2405.15090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T22:35:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a69c942a62a9137f2c32b6768479fda7029490961aacee5f8492d0274a9b536","abstract_canon_sha256":"58855b7227c02733dba2a155f78cfaab205d4a55e8d4147a8e2fc72f891f32a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:44.959776Z","signature_b64":"88fJ9UlH4COuj9l4C6436sjFZs5rmc7mhgtw31RHYB7SmHAWl7DLLXb6AP6a5js5C5eji6KGgkHR5DT8BnKeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cdd80279c579b10f97ee68ee95e274c5cead6f73706453e7f9072d57b7b05d4","last_reissued_at":"2026-07-05T08:22:44.959325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:44.959325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashutosh Nayyar, Dengwang Tang, Pierluigi Nuzzo, Rahul Jain","submitted_at":"2024-05-23T22:35:11Z","abstract_excerpt":"In this paper, we introduce the constrained best mixed arm identification (CBMAI) problem with a fixed budget. This is a pure exploration problem in a stochastic finite armed bandit model. Each arm is associated with a reward and multiple types of costs from unknown distributions. Unlike the unconstrained best arm identification problem, the optimal solution for the CBMAI problem may be a randomized mixture of multiple arms. The goal thus is to find the best mixed arm that maximizes the expected reward subject to constraints on the expected costs with a given learning budget $N$. We propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15090","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/2405.15090/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":"2405.15090","created_at":"2026-07-05T08:22:44.959384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15090v1","created_at":"2026-07-05T08:22:44.959384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15090","created_at":"2026-07-05T08:22:44.959384+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTOYAJ44K6NR","created_at":"2026-07-05T08:22:44.959384+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTOYAJ44K6NRB6L6","created_at":"2026-07-05T08:22:44.959384+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTOYAJ44","created_at":"2026-07-05T08:22:44.959384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.03061","citing_title":"Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR","json":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR.json","graph_json":"https://pith.science/api/pith-number/LTOYAJ44K6NRB6L642HOSXRHJR/graph.json","events_json":"https://pith.science/api/pith-number/LTOYAJ44K6NRB6L642HOSXRHJR/events.json","paper":"https://pith.science/paper/LTOYAJ44"},"agent_actions":{"view_html":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR","download_json":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR.json","view_paper":"https://pith.science/paper/LTOYAJ44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15090&json=true","fetch_graph":"https://pith.science/api/pith-number/LTOYAJ44K6NRB6L642HOSXRHJR/graph.json","fetch_events":"https://pith.science/api/pith-number/LTOYAJ44K6NRB6L642HOSXRHJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR/action/storage_attestation","attest_author":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR/action/author_attestation","sign_citation":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR/action/citation_signature","submit_replication":"https://pith.science/pith/LTOYAJ44K6NRB6L642HOSXRHJR/action/replication_record"}},"created_at":"2026-07-05T08:22:44.959384+00:00","updated_at":"2026-07-05T08:22:44.959384+00:00"}