{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AQB4WAOG6ZRGMMJZ36ELIPP3RF","short_pith_number":"pith:AQB4WAOG","canonical_record":{"source":{"id":"2106.05608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:21:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ddab5368b60b71da05ac31b1bcbd1f20b3ce578e8112b223f1cbbe65ef75f94e","abstract_canon_sha256":"b8158050afc8f7583ea92f8d4a2b428477574bfc5748706dbee458406ff25de4"},"schema_version":"1.0"},"canonical_sha256":"0403cb01c6f662663139df88b43dfb89479160450f9addcd394caf06ed7cc3d4","source":{"kind":"arxiv","id":"2106.05608","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05608","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05608v2","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05608","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"AQB4WAOG6ZRG","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"AQB4WAOG6ZRGMMJZ","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"AQB4WAOG","created_at":"2026-07-05T04:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AQB4WAOG6ZRGMMJZ36ELIPP3RF","target":"record","payload":{"canonical_record":{"source":{"id":"2106.05608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:21:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ddab5368b60b71da05ac31b1bcbd1f20b3ce578e8112b223f1cbbe65ef75f94e","abstract_canon_sha256":"b8158050afc8f7583ea92f8d4a2b428477574bfc5748706dbee458406ff25de4"},"schema_version":"1.0"},"canonical_sha256":"0403cb01c6f662663139df88b43dfb89479160450f9addcd394caf06ed7cc3d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:16.833447Z","signature_b64":"1BSYZRS8YvE6SpqqQs15M5p1gdNCV8RKH3DWSXImGhSgt9LpO9HQ0zKFbM4cfxJLoMLW2RtWG4/zQp9QGkqbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0403cb01c6f662663139df88b43dfb89479160450f9addcd394caf06ed7cc3d4","last_reissued_at":"2026-07-05T04:02:16.832993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:16.832993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.05608","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":"2026-07-05T04:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TLnkZaRR0tcUbHBR81uFLoyXcfwPgH0giirOxvADcUsAk530Pb/4OBUFSStqOlntBo+BPc7qviyakwsgUAHJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:17:10.323674Z"},"content_sha256":"30577ca02cfe45b985e9dfef22eb92d98ba1be35efa55b52940f1c198468f3bd","schema_version":"1.0","event_id":"sha256:30577ca02cfe45b985e9dfef22eb92d98ba1be35efa55b52940f1c198468f3bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AQB4WAOG6ZRGMMJZ36ELIPP3RF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thompson Sampling with a Mixture Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Craig Boutilier, Joey Hong, Manzil Zaheer, Mohammad Ghavamzadeh","submitted_at":"2021-06-10T09:21:07Z","abstract_excerpt":"We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution. This is relevant in multi-task learning, where a learning agent faces different classes of problems. We incorporate this structure in a natural way by initializing TS with a mixture prior, and call the resulting algorithm MixTS. To analyze MixTS, we develop a novel and general proof technique for analyzing the concentration of mixture distributions. We use it to prove Bayes regret bounds for MixTS in both linear bandits and finite-horizon reinforcement learning. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05608","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.05608/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DgS6eTZtWDmlXPdB7j4seKiRl+yK9ofZTQQteI7I/bSoYmana321VnWr5H5CNCvzQ8jyhmkh1stDXtUlFuB7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:17:10.324243Z"},"content_sha256":"a7ee658f633a025255750255bd456b147d4ce55942b1462a878e5ea37d585347","schema_version":"1.0","event_id":"sha256:a7ee658f633a025255750255bd456b147d4ce55942b1462a878e5ea37d585347"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF/bundle.json","state_url":"https://pith.science/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF/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":"2026-08-05T01:17:10Z","links":{"resolver":"https://pith.science/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF","bundle":"https://pith.science/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF/bundle.json","state":"https://pith.science/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQB4WAOG6ZRGMMJZ36ELIPP3RF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AQB4WAOG6ZRGMMJZ36ELIPP3RF","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":"b8158050afc8f7583ea92f8d4a2b428477574bfc5748706dbee458406ff25de4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:21:07Z","title_canon_sha256":"ddab5368b60b71da05ac31b1bcbd1f20b3ce578e8112b223f1cbbe65ef75f94e"},"schema_version":"1.0","source":{"id":"2106.05608","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05608","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05608v2","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05608","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"AQB4WAOG6ZRG","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"AQB4WAOG6ZRGMMJZ","created_at":"2026-07-05T04:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"AQB4WAOG","created_at":"2026-07-05T04:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:a7ee658f633a025255750255bd456b147d4ce55942b1462a878e5ea37d585347","target":"graph","created_at":"2026-07-05T04:02:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.05608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution. This is relevant in multi-task learning, where a learning agent faces different classes of problems. We incorporate this structure in a natural way by initializing TS with a mixture prior, and call the resulting algorithm MixTS. To analyze MixTS, we develop a novel and general proof technique for analyzing the concentration of mixture distributions. We use it to prove Bayes regret bounds for MixTS in both linear bandits and finite-horizon reinforcement learning. Ou","authors_text":"Branislav Kveton, Craig Boutilier, Joey Hong, Manzil Zaheer, Mohammad Ghavamzadeh","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:21:07Z","title":"Thompson Sampling with a Mixture Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05608","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":"sha256:30577ca02cfe45b985e9dfef22eb92d98ba1be35efa55b52940f1c198468f3bd","target":"record","created_at":"2026-07-05T04:02:16Z","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":"b8158050afc8f7583ea92f8d4a2b428477574bfc5748706dbee458406ff25de4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T09:21:07Z","title_canon_sha256":"ddab5368b60b71da05ac31b1bcbd1f20b3ce578e8112b223f1cbbe65ef75f94e"},"schema_version":"1.0","source":{"id":"2106.05608","kind":"arxiv","version":2}},"canonical_sha256":"0403cb01c6f662663139df88b43dfb89479160450f9addcd394caf06ed7cc3d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0403cb01c6f662663139df88b43dfb89479160450f9addcd394caf06ed7cc3d4","first_computed_at":"2026-07-05T04:02:16.832993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:16.832993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1BSYZRS8YvE6SpqqQs15M5p1gdNCV8RKH3DWSXImGhSgt9LpO9HQ0zKFbM4cfxJLoMLW2RtWG4/zQp9QGkqbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:16.833447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05608","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30577ca02cfe45b985e9dfef22eb92d98ba1be35efa55b52940f1c198468f3bd","sha256:a7ee658f633a025255750255bd456b147d4ce55942b1462a878e5ea37d585347"],"state_sha256":"d454e98b456a988ea465a97423114aecce62db7f3ab6a4bd0e0670a4e7098cff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxtUnd2VM8IyX26D+JWy7rOjBJOhHpnsz0vrOSFkqXU0V9n0s7OVO8WZlvdxj4lpkJzm1mbQHGTYZScQqTzDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:17:10.329603Z","bundle_sha256":"2673bdfec616e98e142034d0f1af55162ad3be060427c826d6bd222619583bd4"}}