{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:PRG6GQ6B5LGGYZBLWMYQNDQP76","short_pith_number":"pith:PRG6GQ6B","canonical_record":{"source":{"id":"1105.2879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-05-14T09:51:25Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"d91ce20cafd41bfdd80731677c37dc428c8b229fe35aa3f3bf80235eccf8eece","abstract_canon_sha256":"d0981d863b81c5692e8cbb6794a359045adc204bc791d010278c8460f3ee1dfe"},"schema_version":"1.0"},"canonical_sha256":"7c4de343c1eacc6c642bb331068e0fffa721c6a02ade64423c1f330de5f88bd7","source":{"kind":"arxiv","id":"1105.2879","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1105.2879","created_at":"2026-05-18T03:29:38Z"},{"alias_kind":"arxiv_version","alias_value":"1105.2879v1","created_at":"2026-05-18T03:29:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1105.2879","created_at":"2026-05-18T03:29:38Z"},{"alias_kind":"pith_short_12","alias_value":"PRG6GQ6B5LGG","created_at":"2026-05-18T12:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"PRG6GQ6B5LGGYZBL","created_at":"2026-05-18T12:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"PRG6GQ6B","created_at":"2026-05-18T12:26:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:PRG6GQ6B5LGGYZBLWMYQNDQP76","target":"record","payload":{"canonical_record":{"source":{"id":"1105.2879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-05-14T09:51:25Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"d91ce20cafd41bfdd80731677c37dc428c8b229fe35aa3f3bf80235eccf8eece","abstract_canon_sha256":"d0981d863b81c5692e8cbb6794a359045adc204bc791d010278c8460f3ee1dfe"},"schema_version":"1.0"},"canonical_sha256":"7c4de343c1eacc6c642bb331068e0fffa721c6a02ade64423c1f330de5f88bd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:29:38.708609Z","signature_b64":"Mu+0TLhKGQW/XaiX7qC9JEDrUu34yCng+pX9Cp8ZUpYZLFHNUYSHx5SlLNOAP8GX5sdvHhrfyVu5WZATtmc2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c4de343c1eacc6c642bb331068e0fffa721c6a02ade64423c1f330de5f88bd7","last_reissued_at":"2026-05-18T03:29:38.708158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:29:38.708158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1105.2879","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:29:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qXvB0b9jaxUt4nms+/6WnlnhtFzyNAVwST611xd/1YoWTqJnfIYHP4qJWMmEL9gUMESfas0khKikOw6k6guTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:45:19.816399Z"},"content_sha256":"c04444dc5048eb833c9624ba75ca31126db9214be78bf923f25599b47f8e4916","schema_version":"1.0","event_id":"sha256:c04444dc5048eb833c9624ba75ca31126db9214be78bf923f25599b47f8e4916"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:PRG6GQ6B5LGGYZBLWMYQNDQP76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Bandit Based on Empirical Moments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Akimichi Takemura, Junya Honda","submitted_at":"2011-05-14T09:51:25Z","abstract_excerpt":"In the multiarmed bandit problem a gambler chooses an arm of a slot machine to pull considering a tradeoff between exploration and exploitation. We study the stochastic bandit problem where each arm has a reward distribution supported in a known bounded interval, e.g. [0,1]. For this model, policies which take into account the empirical variances (i.e. second moments) of the arms are known to perform effectively. In this paper, we generalize this idea and we propose a policy which exploits the first d empirical moments for arbitrary d fixed in advance. The asymptotic upper bound of the regret "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1105.2879","kind":"arxiv","version":1},"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":"2026-05-18T03:29:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DojMB8XmYyS5dHzWl9NIZT3ZTgk6azL4ADsnIxx/jxxLrnoj0l2USA+CxOO5e0yV9IHyeJWyOfu7b2qDD95DBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:45:19.816753Z"},"content_sha256":"1565ef22644dd2c73129727202a237e57c6c208c4d1e79a828d32793a560ceef","schema_version":"1.0","event_id":"sha256:1565ef22644dd2c73129727202a237e57c6c208c4d1e79a828d32793a560ceef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76/bundle.json","state_url":"https://pith.science/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76/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":"2026-06-04T21:45:19Z","links":{"resolver":"https://pith.science/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76","bundle":"https://pith.science/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76/bundle.json","state":"https://pith.science/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRG6GQ6B5LGGYZBLWMYQNDQP76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:PRG6GQ6B5LGGYZBLWMYQNDQP76","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":"d0981d863b81c5692e8cbb6794a359045adc204bc791d010278c8460f3ee1dfe","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-05-14T09:51:25Z","title_canon_sha256":"d91ce20cafd41bfdd80731677c37dc428c8b229fe35aa3f3bf80235eccf8eece"},"schema_version":"1.0","source":{"id":"1105.2879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1105.2879","created_at":"2026-05-18T03:29:38Z"},{"alias_kind":"arxiv_version","alias_value":"1105.2879v1","created_at":"2026-05-18T03:29:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1105.2879","created_at":"2026-05-18T03:29:38Z"},{"alias_kind":"pith_short_12","alias_value":"PRG6GQ6B5LGG","created_at":"2026-05-18T12:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"PRG6GQ6B5LGGYZBL","created_at":"2026-05-18T12:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"PRG6GQ6B","created_at":"2026-05-18T12:26:39Z"}],"graph_snapshots":[{"event_id":"sha256:1565ef22644dd2c73129727202a237e57c6c208c4d1e79a828d32793a560ceef","target":"graph","created_at":"2026-05-18T03:29:38Z","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 the multiarmed bandit problem a gambler chooses an arm of a slot machine to pull considering a tradeoff between exploration and exploitation. We study the stochastic bandit problem where each arm has a reward distribution supported in a known bounded interval, e.g. [0,1]. For this model, policies which take into account the empirical variances (i.e. second moments) of the arms are known to perform effectively. In this paper, we generalize this idea and we propose a policy which exploits the first d empirical moments for arbitrary d fixed in advance. The asymptotic upper bound of the regret ","authors_text":"Akimichi Takemura, Junya Honda","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-05-14T09:51:25Z","title":"Stochastic Bandit Based on Empirical Moments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1105.2879","kind":"arxiv","version":1},"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:c04444dc5048eb833c9624ba75ca31126db9214be78bf923f25599b47f8e4916","target":"record","created_at":"2026-05-18T03:29:38Z","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":"d0981d863b81c5692e8cbb6794a359045adc204bc791d010278c8460f3ee1dfe","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-05-14T09:51:25Z","title_canon_sha256":"d91ce20cafd41bfdd80731677c37dc428c8b229fe35aa3f3bf80235eccf8eece"},"schema_version":"1.0","source":{"id":"1105.2879","kind":"arxiv","version":1}},"canonical_sha256":"7c4de343c1eacc6c642bb331068e0fffa721c6a02ade64423c1f330de5f88bd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c4de343c1eacc6c642bb331068e0fffa721c6a02ade64423c1f330de5f88bd7","first_computed_at":"2026-05-18T03:29:38.708158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:29:38.708158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mu+0TLhKGQW/XaiX7qC9JEDrUu34yCng+pX9Cp8ZUpYZLFHNUYSHx5SlLNOAP8GX5sdvHhrfyVu5WZATtmc2Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:29:38.708609Z","signed_message":"canonical_sha256_bytes"},"source_id":"1105.2879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c04444dc5048eb833c9624ba75ca31126db9214be78bf923f25599b47f8e4916","sha256:1565ef22644dd2c73129727202a237e57c6c208c4d1e79a828d32793a560ceef"],"state_sha256":"8fa6426a541ceb64f1a8d99ad16168fbc21fd76f34e2d2ebebe4cf26f8ae024d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0Xpz6MaizupQSdI93VZ5nIeuU9oZ/RLM0al6Qxr3SucDwGvHR2dzzlfXokkCm4eteWDf40VFr/NjAB4SpxMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T21:45:19.818778Z","bundle_sha256":"2e4cf8de238fa23eebd3c4c34f68eb485b43af31f7aad0f0ffbddcca225b8956"}}