{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VBK4IMZDZ5JYALXWPX4JP5QE4T","short_pith_number":"pith:VBK4IMZD","schema_version":"1.0","canonical_sha256":"a855c43323cf53802ef67df897f604e4ebf8b704cf8c3856e8838757c799fc80","source":{"kind":"arxiv","id":"1710.06360","version":2},"attestation_state":"computed","paper":{"title":"Good Arm Identification via Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Atsuyoshi Nakamura, Hideaki Kano, Junya Honda, Kentaro Matsuura, Kentaro Sakamaki, Masashi Sugiyama","submitted_at":"2017-10-17T16:08:16Z","abstract_excerpt":"We consider a novel stochastic multi-armed bandit problem called {\\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold. GAI is a pure-exploration problem that a single agent repeats a process of outputting an arm as soon as it is identified as a good one before confirming the other arms are actually not good. The objective of GAI is to minimize the number of samples for each process. We find that GAI faces a new kind of dilemma, the {\\em exploration-exploitation dilemma of confidence}, which is different diffi"},"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":"1710.06360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-17T16:08:16Z","cross_cats_sorted":[],"title_canon_sha256":"daa91c3d20ee9d8d7c2e6dffc1920eba306862a09ddf8f06e9ef49829c583fd4","abstract_canon_sha256":"ed5a469490074385a813c59857546b918a2dad967d1bd4421873d446fe77501a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:52.796661Z","signature_b64":"BL6R7cXFFkmvffiUKXZbCtzeX+uowqMCAJeylEB805EWRU3O6XhA01bg6RHv9022Tq42hHYATfQMAYBOeFYXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a855c43323cf53802ef67df897f604e4ebf8b704cf8c3856e8838757c799fc80","last_reissued_at":"2026-05-18T00:23:52.795925Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:52.795925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Good Arm Identification via Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Atsuyoshi Nakamura, Hideaki Kano, Junya Honda, Kentaro Matsuura, Kentaro Sakamaki, Masashi Sugiyama","submitted_at":"2017-10-17T16:08:16Z","abstract_excerpt":"We consider a novel stochastic multi-armed bandit problem called {\\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold. GAI is a pure-exploration problem that a single agent repeats a process of outputting an arm as soon as it is identified as a good one before confirming the other arms are actually not good. The objective of GAI is to minimize the number of samples for each process. We find that GAI faces a new kind of dilemma, the {\\em exploration-exploitation dilemma of confidence}, which is different diffi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06360","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.06360","created_at":"2026-05-18T00:23:52.796028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.06360v2","created_at":"2026-05-18T00:23:52.796028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06360","created_at":"2026-05-18T00:23:52.796028+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBK4IMZDZ5JY","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBK4IMZDZ5JYALXW","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBK4IMZD","created_at":"2026-05-18T12:31:49.984773+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/VBK4IMZDZ5JYALXWPX4JP5QE4T","json":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T.json","graph_json":"https://pith.science/api/pith-number/VBK4IMZDZ5JYALXWPX4JP5QE4T/graph.json","events_json":"https://pith.science/api/pith-number/VBK4IMZDZ5JYALXWPX4JP5QE4T/events.json","paper":"https://pith.science/paper/VBK4IMZD"},"agent_actions":{"view_html":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T","download_json":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T.json","view_paper":"https://pith.science/paper/VBK4IMZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.06360&json=true","fetch_graph":"https://pith.science/api/pith-number/VBK4IMZDZ5JYALXWPX4JP5QE4T/graph.json","fetch_events":"https://pith.science/api/pith-number/VBK4IMZDZ5JYALXWPX4JP5QE4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T/action/storage_attestation","attest_author":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T/action/author_attestation","sign_citation":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T/action/citation_signature","submit_replication":"https://pith.science/pith/VBK4IMZDZ5JYALXWPX4JP5QE4T/action/replication_record"}},"created_at":"2026-05-18T00:23:52.796028+00:00","updated_at":"2026-05-18T00:23:52.796028+00:00"}