{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:6NU55XKTD46CGSDRPVBBNZRSO6","short_pith_number":"pith:6NU55XKT","canonical_record":{"source":{"id":"1202.2277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-02-10T15:00:53Z","cross_cats_sorted":["math.PR","stat.TH"],"title_canon_sha256":"66468225ad694d7983987a0ba40958d8c9b6c424a519832b5d737533476302f1","abstract_canon_sha256":"ccaa2b27557305dc5d8b950d91f36c39a67dcde4ed0c8feee0b3c5810602be76"},"schema_version":"1.0"},"canonical_sha256":"f369dedd531f3c2348717d4216e63277be94a9a9458e5a1fd40cd55e828ea09a","source":{"kind":"arxiv","id":"1202.2277","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.2277","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"1202.2277v2","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.2277","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"6NU55XKTD46C","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"6NU55XKTD46CGSDR","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"6NU55XKT","created_at":"2026-05-18T12:26:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:6NU55XKTD46CGSDRPVBBNZRSO6","target":"record","payload":{"canonical_record":{"source":{"id":"1202.2277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-02-10T15:00:53Z","cross_cats_sorted":["math.PR","stat.TH"],"title_canon_sha256":"66468225ad694d7983987a0ba40958d8c9b6c424a519832b5d737533476302f1","abstract_canon_sha256":"ccaa2b27557305dc5d8b950d91f36c39a67dcde4ed0c8feee0b3c5810602be76"},"schema_version":"1.0"},"canonical_sha256":"f369dedd531f3c2348717d4216e63277be94a9a9458e5a1fd40cd55e828ea09a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:03.557947Z","signature_b64":"cmtdQ3T0hxIJc59LwqcScEKxMz0B2syZLJVx/iWYF45oIJ3nVXMsiE3JHEk9R9ofYFpjZO28yw/Gr6n9B2rzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f369dedd531f3c2348717d4216e63277be94a9a9458e5a1fd40cd55e828ea09a","last_reissued_at":"2026-05-18T04:02:03.557330Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:03.557330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.2277","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSVnzTUrcGY1EVrDHBIL67Rh9NfQCw9LECSDmNbEj0C5cSJ2ih9jeyK8gh4mtVotrz8bDcvcjHlQp1jucvJsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:27:08.618158Z"},"content_sha256":"4540b458e0a2e6e47b7ab5f914e28b410e3df16f7985072d502450690c22d4e8","schema_version":"1.0","event_id":"sha256:4540b458e0a2e6e47b7ab5f914e28b410e3df16f7985072d502450690c22d4e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:6NU55XKTD46CGSDRPVBBNZRSO6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite-time Regret Bound of a Bandit Algorithm for the Semi-bounded Support Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Akimichi Takemura, Junya Honda","submitted_at":"2012-02-10T15:00:53Z","abstract_excerpt":"In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g. [0,1]. However, the derived regret bound is described in an asymptotic form and the performance in finite time has been unknown. We inspect this policy and derive a finite-time regret bound by refining large deviation probabilities to a simple finite form. Further, this observation reveals that the assumption on the lower-boundedness of the support is not essent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.2277","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6C/VjXULn3vvGM9TjaZvnhUhSyXIIufmNdpj+9UadGsx4SnKDUfrJZvnCGGxY9cN6cu7hjVqfd12jW+4g7oMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:27:08.618891Z"},"content_sha256":"c965f6b2a3fb171b203e0fa65d2c7397bf778ca769254e43c845b17a591910de","schema_version":"1.0","event_id":"sha256:c965f6b2a3fb171b203e0fa65d2c7397bf778ca769254e43c845b17a591910de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NU55XKTD46CGSDRPVBBNZRSO6/bundle.json","state_url":"https://pith.science/pith/6NU55XKTD46CGSDRPVBBNZRSO6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NU55XKTD46CGSDRPVBBNZRSO6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T22:27:08Z","links":{"resolver":"https://pith.science/pith/6NU55XKTD46CGSDRPVBBNZRSO6","bundle":"https://pith.science/pith/6NU55XKTD46CGSDRPVBBNZRSO6/bundle.json","state":"https://pith.science/pith/6NU55XKTD46CGSDRPVBBNZRSO6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NU55XKTD46CGSDRPVBBNZRSO6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:6NU55XKTD46CGSDRPVBBNZRSO6","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":"ccaa2b27557305dc5d8b950d91f36c39a67dcde4ed0c8feee0b3c5810602be76","cross_cats_sorted":["math.PR","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-02-10T15:00:53Z","title_canon_sha256":"66468225ad694d7983987a0ba40958d8c9b6c424a519832b5d737533476302f1"},"schema_version":"1.0","source":{"id":"1202.2277","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.2277","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"1202.2277v2","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.2277","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"6NU55XKTD46C","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"6NU55XKTD46CGSDR","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"6NU55XKT","created_at":"2026-05-18T12:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:c965f6b2a3fb171b203e0fa65d2c7397bf778ca769254e43c845b17a591910de","target":"graph","created_at":"2026-05-18T04:02:03Z","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"},"paper":{"abstract_excerpt":"In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g. [0,1]. However, the derived regret bound is described in an asymptotic form and the performance in finite time has been unknown. We inspect this policy and derive a finite-time regret bound by refining large deviation probabilities to a simple finite form. Further, this observation reveals that the assumption on the lower-boundedness of the support is not essent","authors_text":"Akimichi Takemura, Junya Honda","cross_cats":["math.PR","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-02-10T15:00:53Z","title":"Finite-time Regret Bound of a Bandit Algorithm for the Semi-bounded Support Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.2277","kind":"arxiv","version":2},"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":"sha256:4540b458e0a2e6e47b7ab5f914e28b410e3df16f7985072d502450690c22d4e8","target":"record","created_at":"2026-05-18T04:02:03Z","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":"ccaa2b27557305dc5d8b950d91f36c39a67dcde4ed0c8feee0b3c5810602be76","cross_cats_sorted":["math.PR","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-02-10T15:00:53Z","title_canon_sha256":"66468225ad694d7983987a0ba40958d8c9b6c424a519832b5d737533476302f1"},"schema_version":"1.0","source":{"id":"1202.2277","kind":"arxiv","version":2}},"canonical_sha256":"f369dedd531f3c2348717d4216e63277be94a9a9458e5a1fd40cd55e828ea09a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f369dedd531f3c2348717d4216e63277be94a9a9458e5a1fd40cd55e828ea09a","first_computed_at":"2026-05-18T04:02:03.557330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:03.557330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cmtdQ3T0hxIJc59LwqcScEKxMz0B2syZLJVx/iWYF45oIJ3nVXMsiE3JHEk9R9ofYFpjZO28yw/Gr6n9B2rzDA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:03.557947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.2277","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4540b458e0a2e6e47b7ab5f914e28b410e3df16f7985072d502450690c22d4e8","sha256:c965f6b2a3fb171b203e0fa65d2c7397bf778ca769254e43c845b17a591910de"],"state_sha256":"8dc349f13c890a360aa50e8f1fb88d950a2968fc382fc86c55ab2637312de355"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81UjZiNC5SkI7JadhZ3HTkk58Wqxak2N+/456gzBOyohr79/rwwuTZNAZ6QacQ9Y7P+dmx/xtRaPI0Ufo8rMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T22:27:08.622777Z","bundle_sha256":"6586be77c9c15c50fb92b87a9ef12950f9e3872facfabeb2fa73075a4d21f1e6"}}