{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:MLEMPDXKK3LH5JVZHMSOQV2YH6","short_pith_number":"pith:MLEMPDXK","canonical_record":{"source":{"id":"1506.00779","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-02T07:42:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6ece93784f5f49289dbb20fbdbc39b7d0ce7a770cc2d1f495536d6d8845e3548","abstract_canon_sha256":"564abe3a9849710859905c7a706ffaa23caf3db0b1bed0fe1f700a4bf627f3f0"},"schema_version":"1.0"},"canonical_sha256":"62c8c78eea56d67ea6b93b24e857583fb8b1dfc80d7a642cdd897bbca6d03ce6","source":{"kind":"arxiv","id":"1506.00779","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.00779","created_at":"2026-05-17T23:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1506.00779v3","created_at":"2026-05-17T23:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00779","created_at":"2026-05-17T23:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"MLEMPDXKK3LH","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"MLEMPDXKK3LH5JVZ","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"MLEMPDXK","created_at":"2026-05-18T12:29:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:MLEMPDXKK3LH5JVZHMSOQV2YH6","target":"record","payload":{"canonical_record":{"source":{"id":"1506.00779","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-02T07:42:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6ece93784f5f49289dbb20fbdbc39b7d0ce7a770cc2d1f495536d6d8845e3548","abstract_canon_sha256":"564abe3a9849710859905c7a706ffaa23caf3db0b1bed0fe1f700a4bf627f3f0"},"schema_version":"1.0"},"canonical_sha256":"62c8c78eea56d67ea6b93b24e857583fb8b1dfc80d7a642cdd897bbca6d03ce6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:47.407777Z","signature_b64":"gKhsiBHX0xdc3jVgN4oOnQeBXaoKs8RsCnVdgxZec5SWzq9Dqo+i3FnfVA25HPj0iystMttt2PobARk1jwVmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c8c78eea56d67ea6b93b24e857583fb8b1dfc80d7a642cdd897bbca6d03ce6","last_reissued_at":"2026-05-17T23:50:47.407011Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:47.407011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.00779","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ttkLsrAxG3fwTWR8OcMLdiPdHv48rlXJIL5RxknH56+ATcY1irKoL/3N/bhFZznXx/UTNaVxf93yuZPS69iKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:55:59.347592Z"},"content_sha256":"031c3bc634dea690eed22d6ddd46940f160f7df3b7162b82445b9604b5a8feb1","schema_version":"1.0","event_id":"sha256:031c3bc634dea690eed22d6ddd46940f160f7df3b7162b82445b9604b5a8feb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:MLEMPDXKK3LH5JVZHMSOQV2YH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hiroshi Nakagawa, Junpei Komiyama, Junya Honda","submitted_at":"2015-06-02T07:42:16Z","abstract_excerpt":"We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the standard single-play MAB problem. In this paper, we propose the multiple-play Thompson sampling (MP-TS) algorithm, an extension of TS to the multiple-play MAB problem, and discuss its regret analysis. We prove that MP-TS for binary rewards has the optimal regret upper bound that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00779","kind":"arxiv","version":3},"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":"2026-05-17T23:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kufPeJuLLW0jMwYx4CCR9kr5zZ6HJ9R8SmYvJ2AW1rheXtSqZlFCwwL7FzGbqqcgPfWZCxsCSwsvuDS/DG4zAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:55:59.348191Z"},"content_sha256":"3a5d321b3fc09ce11ea367d1dd566911c86d8d61d880990f84fffa994b56c43c","schema_version":"1.0","event_id":"sha256:3a5d321b3fc09ce11ea367d1dd566911c86d8d61d880990f84fffa994b56c43c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6/bundle.json","state_url":"https://pith.science/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6/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":"2026-06-07T17:55:59Z","links":{"resolver":"https://pith.science/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6","bundle":"https://pith.science/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6/bundle.json","state":"https://pith.science/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLEMPDXKK3LH5JVZHMSOQV2YH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:MLEMPDXKK3LH5JVZHMSOQV2YH6","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":"564abe3a9849710859905c7a706ffaa23caf3db0b1bed0fe1f700a4bf627f3f0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-02T07:42:16Z","title_canon_sha256":"6ece93784f5f49289dbb20fbdbc39b7d0ce7a770cc2d1f495536d6d8845e3548"},"schema_version":"1.0","source":{"id":"1506.00779","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.00779","created_at":"2026-05-17T23:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"1506.00779v3","created_at":"2026-05-17T23:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00779","created_at":"2026-05-17T23:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"MLEMPDXKK3LH","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"MLEMPDXKK3LH5JVZ","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"MLEMPDXK","created_at":"2026-05-18T12:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:3a5d321b3fc09ce11ea367d1dd566911c86d8d61d880990f84fffa994b56c43c","target":"graph","created_at":"2026-05-17T23:50:47Z","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":"We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the standard single-play MAB problem. In this paper, we propose the multiple-play Thompson sampling (MP-TS) algorithm, an extension of TS to the multiple-play MAB problem, and discuss its regret analysis. We prove that MP-TS for binary rewards has the optimal regret upper bound that","authors_text":"Hiroshi Nakagawa, Junpei Komiyama, Junya Honda","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-02T07:42:16Z","title":"Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00779","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":"sha256:031c3bc634dea690eed22d6ddd46940f160f7df3b7162b82445b9604b5a8feb1","target":"record","created_at":"2026-05-17T23:50:47Z","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":"564abe3a9849710859905c7a706ffaa23caf3db0b1bed0fe1f700a4bf627f3f0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-02T07:42:16Z","title_canon_sha256":"6ece93784f5f49289dbb20fbdbc39b7d0ce7a770cc2d1f495536d6d8845e3548"},"schema_version":"1.0","source":{"id":"1506.00779","kind":"arxiv","version":3}},"canonical_sha256":"62c8c78eea56d67ea6b93b24e857583fb8b1dfc80d7a642cdd897bbca6d03ce6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62c8c78eea56d67ea6b93b24e857583fb8b1dfc80d7a642cdd897bbca6d03ce6","first_computed_at":"2026-05-17T23:50:47.407011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:47.407011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gKhsiBHX0xdc3jVgN4oOnQeBXaoKs8RsCnVdgxZec5SWzq9Dqo+i3FnfVA25HPj0iystMttt2PobARk1jwVmAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:47.407777Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.00779","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:031c3bc634dea690eed22d6ddd46940f160f7df3b7162b82445b9604b5a8feb1","sha256:3a5d321b3fc09ce11ea367d1dd566911c86d8d61d880990f84fffa994b56c43c"],"state_sha256":"242c489c7e92b3f61a1025e8cd2d04a184e7cdd01b8a3998f99ab881256f9295"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wNL03stlVyzeQ5aha2jeE0to5gVZ0aV43ahxI9sjC6SnEYi1NXVF8LNWewd8ViO+zrGmS3GztO77fNCDT6iEDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T17:55:59.350989Z","bundle_sha256":"c87412467ea90109a97f2c3a30e3e46dd163941a6b1028e850eb333afd54030d"}}