{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HMIYIGCI7U3ADJKN3ETHTCE7ZI","short_pith_number":"pith:HMIYIGCI","canonical_record":{"source":{"id":"2110.15688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1","abstract_canon_sha256":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac"},"schema_version":"1.0"},"canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","source":{"kind":"arxiv","id":"2110.15688","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15688","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15688v1","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15688","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"HMIYIGCI7U3A","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"HMIYIGCI7U3ADJKN","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"HMIYIGCI","created_at":"2026-07-05T03:27:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HMIYIGCI7U3ADJKN3ETHTCE7ZI","target":"record","payload":{"canonical_record":{"source":{"id":"2110.15688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1","abstract_canon_sha256":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac"},"schema_version":"1.0"},"canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:12.797107Z","signature_b64":"LFuuZcGTjw+NW1+G9LDWw5p10fNvo4Nsypga8lcOWE3uF0SqoQoiL6YnKhcw04r7AcHbQeVKnSqINEwQmR15Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","last_reissued_at":"2026-07-05T03:27:12.796647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:12.796647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.15688","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":"2026-07-05T03:27:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGjm8H1AWM8H7LRgCO+4qXGuwTC8aEz6H/2lhFccVHxxy9tBflYFD8fL6fRfrOPYo842VzqmFwH5KbOr2VbNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:49:43.859082Z"},"content_sha256":"6c615f25c17cae9557671e1b4b2b5ad3595f2486a8b8cd0a2443da1a202a0eed","schema_version":"1.0","event_id":"sha256:6c615f25c17cae9557671e1b4b2b5ad3595f2486a8b8cd0a2443da1a202a0eed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HMIYIGCI7U3ADJKN3ETHTCE7ZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Bayesian Optimistic Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brendan O'Donoghue, Tor Lattimore","submitted_at":"2021-10-29T11:28:29Z","abstract_excerpt":"We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling policy. We provide a new analysis showing that any algorithm producing policies in the optimistic set enjoys $\\tilde O(\\sqrt{AT})$ Bayesian regret for a problem with $A$ actions after $T$ rounds. We extend the regret analysis for optimistic policies to bilinear saddle-point problems which include zero-sum matrix games and constrained bandits as special cases. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15688","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.15688/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":"2026-07-05T03:27:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q80CmCtF0roLrC1JnRwXw1/mtiL6xuAhfGwvAJJO3d9a4WLKdNc3XghTGpwwkWYzaXRcpS+dJlmT3z4qrqUnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:49:43.859633Z"},"content_sha256":"16c11f16c61658a825417d1f85806c927c151066005245b834c27fe339b51968","schema_version":"1.0","event_id":"sha256:16c11f16c61658a825417d1f85806c927c151066005245b834c27fe339b51968"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/bundle.json","state_url":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/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":"2026-08-11T01:49:43Z","links":{"resolver":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI","bundle":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/bundle.json","state":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HMIYIGCI7U3ADJKN3ETHTCE7ZI","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":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1"},"schema_version":"1.0","source":{"id":"2110.15688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15688","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15688v1","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15688","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"HMIYIGCI7U3A","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"HMIYIGCI7U3ADJKN","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"HMIYIGCI","created_at":"2026-07-05T03:27:12Z"}],"graph_snapshots":[{"event_id":"sha256:16c11f16c61658a825417d1f85806c927c151066005245b834c27fe339b51968","target":"graph","created_at":"2026-07-05T03:27:12Z","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/2110.15688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling policy. We provide a new analysis showing that any algorithm producing policies in the optimistic set enjoys $\\tilde O(\\sqrt{AT})$ Bayesian regret for a problem with $A$ actions after $T$ rounds. We extend the regret analysis for optimistic policies to bilinear saddle-point problems which include zero-sum matrix games and constrained bandits as special cases. I","authors_text":"Brendan O'Donoghue, Tor Lattimore","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","title":"Variational Bayesian Optimistic Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15688","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":"sha256:6c615f25c17cae9557671e1b4b2b5ad3595f2486a8b8cd0a2443da1a202a0eed","target":"record","created_at":"2026-07-05T03:27:12Z","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":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1"},"schema_version":"1.0","source":{"id":"2110.15688","kind":"arxiv","version":1}},"canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","first_computed_at":"2026-07-05T03:27:12.796647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:12.796647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LFuuZcGTjw+NW1+G9LDWw5p10fNvo4Nsypga8lcOWE3uF0SqoQoiL6YnKhcw04r7AcHbQeVKnSqINEwQmR15Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:12.797107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c615f25c17cae9557671e1b4b2b5ad3595f2486a8b8cd0a2443da1a202a0eed","sha256:16c11f16c61658a825417d1f85806c927c151066005245b834c27fe339b51968"],"state_sha256":"0828a124e0b72a1e8b0d21f7e6ae53d157cd3afd0070507897fa2cf0155799ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7DC6ylxanBdzkM4nJVbp4EFmTnxAjjtsTiYB0B3dDnC/lWDfFUABgt6qlzs1HSrU0Oh50p7mVwrRdSNTu/CDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:49:43.865150Z","bundle_sha256":"d2c332341533de9740b74b080536d9ae2c10e72a5f1bf0ba27150ae15809420e"}}