{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3XTWGO6RHY3HSLHOR6G7ZPLB67","short_pith_number":"pith:3XTWGO6R","schema_version":"1.0","canonical_sha256":"dde7633bd13e36792cee8f8dfcbd61f7fbdaa85f6a64dc0024962127ea1953b4","source":{"kind":"arxiv","id":"2109.08229","version":5},"attestation_state":"computed","paper":{"title":"Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"econ.EM","authors_text":"Chao Qin, Junpei Komiyama, Kaito Ariu, Kenichiro McAlinn, Masahiro Kato","submitted_at":"2021-09-16T21:27:03Z","abstract_excerpt":"We consider the \"policy choice\" problem -- otherwise known as best arm identification in the bandit literature -- proposed by Kasy and Sautmann (2021) for adaptive experimental design. Theorem 1 of Kasy and Sautmann (2021) provides three asymptotic results that give theoretical guarantees for exploration sampling developed for this setting. We first show that the proof of Theorem 1 (1) has technical issues, and the proof and statement of Theorem 1 (2) are incorrect. We then show, through a counterexample, that Theorem 1 (3) is false. For the former two, we correct the statements and provide ri"},"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":"2109.08229","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-09-16T21:27:03Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"ccc268e3d7140a5f4c6d421e92c73fe8b742a73b5b016b27e5daeb51385cff6e","abstract_canon_sha256":"597f446b1a1dca73b9d90d3bacfb87e99e2cd3141c4ba1e5466c06aee3623704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:46.719129Z","signature_b64":"aRjVCT7PqLRglLdN3E7tvheyFMEVmqHpJ9XBEx3/T9f8OsZBeGZ0b12NGr6v3PHr4DkeF9/l89hgzUZJN38wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dde7633bd13e36792cee8f8dfcbd61f7fbdaa85f6a64dc0024962127ea1953b4","last_reissued_at":"2026-07-05T03:34:46.718659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:46.718659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"econ.EM","authors_text":"Chao Qin, Junpei Komiyama, Kaito Ariu, Kenichiro McAlinn, Masahiro Kato","submitted_at":"2021-09-16T21:27:03Z","abstract_excerpt":"We consider the \"policy choice\" problem -- otherwise known as best arm identification in the bandit literature -- proposed by Kasy and Sautmann (2021) for adaptive experimental design. Theorem 1 of Kasy and Sautmann (2021) provides three asymptotic results that give theoretical guarantees for exploration sampling developed for this setting. We first show that the proof of Theorem 1 (1) has technical issues, and the proof and statement of Theorem 1 (2) are incorrect. We then show, through a counterexample, that Theorem 1 (3) is false. For the former two, we correct the statements and provide ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08229","kind":"arxiv","version":5},"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/2109.08229/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":"2109.08229","created_at":"2026-07-05T03:34:46.718717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08229v5","created_at":"2026-07-05T03:34:46.718717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08229","created_at":"2026-07-05T03:34:46.718717+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XTWGO6RHY3H","created_at":"2026-07-05T03:34:46.718717+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XTWGO6RHY3HSLHO","created_at":"2026-07-05T03:34:46.718717+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XTWGO6R","created_at":"2026-07-05T03:34:46.718717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07726","citing_title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17952","citing_title":"Causal inference for social network formation","ref_index":257,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67","json":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67.json","graph_json":"https://pith.science/api/pith-number/3XTWGO6RHY3HSLHOR6G7ZPLB67/graph.json","events_json":"https://pith.science/api/pith-number/3XTWGO6RHY3HSLHOR6G7ZPLB67/events.json","paper":"https://pith.science/paper/3XTWGO6R"},"agent_actions":{"view_html":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67","download_json":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67.json","view_paper":"https://pith.science/paper/3XTWGO6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08229&json=true","fetch_graph":"https://pith.science/api/pith-number/3XTWGO6RHY3HSLHOR6G7ZPLB67/graph.json","fetch_events":"https://pith.science/api/pith-number/3XTWGO6RHY3HSLHOR6G7ZPLB67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67/action/storage_attestation","attest_author":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67/action/author_attestation","sign_citation":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67/action/citation_signature","submit_replication":"https://pith.science/pith/3XTWGO6RHY3HSLHOR6G7ZPLB67/action/replication_record"}},"created_at":"2026-07-05T03:34:46.718717+00:00","updated_at":"2026-07-05T03:34:46.718717+00:00"}