{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4AJEOZMIL3UJCPPJI7ROPJD365","short_pith_number":"pith:4AJEOZMI","schema_version":"1.0","canonical_sha256":"e0124765885ee8913de947e2e7a47bf743c902016f2c8e43e06478a3888779a5","source":{"kind":"arxiv","id":"2308.10238","version":3},"attestation_state":"computed","paper":{"title":"Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Shintaro Nakamura","submitted_at":"2023-08-20T11:56:02Z","abstract_excerpt":"We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\\in\\{1, \\ldots, d\\}$ follows an unknown distribution with mean $\\mu_s$. In each time step, a player pulls a single arm and observes its reward. The player's goal is to identify the optimal \\emph{action} $\\boldsymbol{\\pi}^{*} = \\argmax_{\\boldsymbol{\\pi} \\in \\mathcal{A}} \\boldsymbol{\\mu}^{\\top}\\boldsymbol{\\pi}$ from a finite-sized real-valued \\emph{action set} $\\mathcal{A}\\subset \\mathbb{R}^{d}$ with as few arm pu"},"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":"2308.10238","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-20T11:56:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"05dd85461624a238a1f9c9526f74c0eca9051b963f06d23a9a68e33420c2fbe0","abstract_canon_sha256":"78a28b8cdc52b0bb94d1da7a51ad783537086e043facdd25b4cc566a4ad94e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:52.432667Z","signature_b64":"gFUvYAqLvavYuGnMSq1kM1UM3zKwqDeSxxksaH3s5jqE2XIg4vwNRe2CeulzVb7ASHUHUqlThUICiySdLoAPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0124765885ee8913de947e2e7a47bf743c902016f2c8e43e06478a3888779a5","last_reissued_at":"2026-07-05T07:12:52.430037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:52.430037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Shintaro Nakamura","submitted_at":"2023-08-20T11:56:02Z","abstract_excerpt":"We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\\in\\{1, \\ldots, d\\}$ follows an unknown distribution with mean $\\mu_s$. In each time step, a player pulls a single arm and observes its reward. The player's goal is to identify the optimal \\emph{action} $\\boldsymbol{\\pi}^{*} = \\argmax_{\\boldsymbol{\\pi} \\in \\mathcal{A}} \\boldsymbol{\\mu}^{\\top}\\boldsymbol{\\pi}$ from a finite-sized real-valued \\emph{action set} $\\mathcal{A}\\subset \\mathbb{R}^{d}$ with as few arm pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10238","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/2308.10238/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":"2308.10238","created_at":"2026-07-05T07:12:52.430092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10238v3","created_at":"2026-07-05T07:12:52.430092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10238","created_at":"2026-07-05T07:12:52.430092+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AJEOZMIL3UJ","created_at":"2026-07-05T07:12:52.430092+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AJEOZMIL3UJCPPJ","created_at":"2026-07-05T07:12:52.430092+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AJEOZMI","created_at":"2026-07-05T07:12:52.430092+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/4AJEOZMIL3UJCPPJI7ROPJD365","json":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365.json","graph_json":"https://pith.science/api/pith-number/4AJEOZMIL3UJCPPJI7ROPJD365/graph.json","events_json":"https://pith.science/api/pith-number/4AJEOZMIL3UJCPPJI7ROPJD365/events.json","paper":"https://pith.science/paper/4AJEOZMI"},"agent_actions":{"view_html":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365","download_json":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365.json","view_paper":"https://pith.science/paper/4AJEOZMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10238&json=true","fetch_graph":"https://pith.science/api/pith-number/4AJEOZMIL3UJCPPJI7ROPJD365/graph.json","fetch_events":"https://pith.science/api/pith-number/4AJEOZMIL3UJCPPJI7ROPJD365/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365/action/storage_attestation","attest_author":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365/action/author_attestation","sign_citation":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365/action/citation_signature","submit_replication":"https://pith.science/pith/4AJEOZMIL3UJCPPJI7ROPJD365/action/replication_record"}},"created_at":"2026-07-05T07:12:52.430092+00:00","updated_at":"2026-07-05T07:12:52.430092+00:00"}