{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4AJEOZMIL3UJCPPJI7ROPJD365","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"78a28b8cdc52b0bb94d1da7a51ad783537086e043facdd25b4cc566a4ad94e1c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-20T11:56:02Z","title_canon_sha256":"05dd85461624a238a1f9c9526f74c0eca9051b963f06d23a9a68e33420c2fbe0"},"schema_version":"1.0","source":{"id":"2308.10238","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10238","created_at":"2026-07-05T07:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10238v3","created_at":"2026-07-05T07:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10238","created_at":"2026-07-05T07:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"4AJEOZMIL3UJ","created_at":"2026-07-05T07:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"4AJEOZMIL3UJCPPJ","created_at":"2026-07-05T07:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"4AJEOZMI","created_at":"2026-07-05T07:12:52Z"}],"graph_snapshots":[{"event_id":"sha256:8495f561cbd267432b475a88b910433bd1cfc516654adb5d327831275784ef95","target":"graph","created_at":"2026-07-05T07:12:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.10238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Masashi Sugiyama, Shintaro Nakamura","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-20T11:56:02Z","title":"Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10238","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2f2a572729d03f86d9765228d7147b7bd1fc78cf9fb526b30c9cf5cc7009e8d","target":"record","created_at":"2026-07-05T07:12:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"78a28b8cdc52b0bb94d1da7a51ad783537086e043facdd25b4cc566a4ad94e1c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-20T11:56:02Z","title_canon_sha256":"05dd85461624a238a1f9c9526f74c0eca9051b963f06d23a9a68e33420c2fbe0"},"schema_version":"1.0","source":{"id":"2308.10238","kind":"arxiv","version":3}},"canonical_sha256":"e0124765885ee8913de947e2e7a47bf743c902016f2c8e43e06478a3888779a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0124765885ee8913de947e2e7a47bf743c902016f2c8e43e06478a3888779a5","first_computed_at":"2026-07-05T07:12:52.430037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:52.430037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFUvYAqLvavYuGnMSq1kM1UM3zKwqDeSxxksaH3s5jqE2XIg4vwNRe2CeulzVb7ASHUHUqlThUICiySdLoAPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:52.432667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10238","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2f2a572729d03f86d9765228d7147b7bd1fc78cf9fb526b30c9cf5cc7009e8d","sha256:8495f561cbd267432b475a88b910433bd1cfc516654adb5d327831275784ef95"],"state_sha256":"b8993fc6ea4dfb30738887396d1cde61239b4c2d19d21dbb1f89802ba0ea249d"}