{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:QPUR34BQNOUO4T3NNJL5EDKYOS","short_pith_number":"pith:QPUR34BQ","canonical_record":{"source":{"id":"1202.4473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-20T21:29:28Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"d17e972425e79573018db17269f848376225811db3a8b87be1f7a57dbb000942","abstract_canon_sha256":"d4cb119c3fa4578fdb877d9675f21a48872d0cff5a9145338b4783a510d93250"},"schema_version":"1.0"},"canonical_sha256":"83e91df0306ba8ee4f6d6a57d20d58749db82e84f071bf42fc91159b0e7d0ae6","source":{"kind":"arxiv","id":"1202.4473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.4473","created_at":"2026-05-18T04:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"1202.4473v1","created_at":"2026-05-18T04:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.4473","created_at":"2026-05-18T04:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"QPUR34BQNOUO","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"QPUR34BQNOUO4T3N","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"QPUR34BQ","created_at":"2026-05-18T12:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:QPUR34BQNOUO4T3NNJL5EDKYOS","target":"record","payload":{"canonical_record":{"source":{"id":"1202.4473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-20T21:29:28Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"d17e972425e79573018db17269f848376225811db3a8b87be1f7a57dbb000942","abstract_canon_sha256":"d4cb119c3fa4578fdb877d9675f21a48872d0cff5a9145338b4783a510d93250"},"schema_version":"1.0"},"canonical_sha256":"83e91df0306ba8ee4f6d6a57d20d58749db82e84f071bf42fc91159b0e7d0ae6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:01:50.557022Z","signature_b64":"HAcPoL+Esk6k/AjN1iM/H4zkB9XMD17Zy7sKIzvxby84CaWgfBat/mPLE5VSlI7uxwGeTb0IGQ5jTvn4F0NSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83e91df0306ba8ee4f6d6a57d20d58749db82e84f071bf42fc91159b0e7d0ae6","last_reissued_at":"2026-05-18T04:01:50.556583Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:01:50.556583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.4473","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":"2026-05-18T04:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAUmCuppCjbJHaSN/MbluEKjlmECxfizktoqPzl6PKPoiW2UfT8tRMOxSYYZ0KizC9Et1Y+LBgfLrQzXLOQKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:50:49.040837Z"},"content_sha256":"f3b211cd4335f7b858cf80cc8119e997126251679587408f092e718dbbfc7620","schema_version":"1.0","event_id":"sha256:f3b211cd4335f7b858cf80cc8119e997126251679587408f092e718dbbfc7620"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:QPUR34BQNOUO4T3NNJL5EDKYOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The best of both worlds: stochastic and adversarial bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Aleksandrs Slivkins, Sebastien Bubeck","submitted_at":"2012-02-20T21:29:28Z","abstract_excerpt":"We present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifically, SAO combines the square-root worst-case regret of Exp3 (Auer et al., SIAM J. on Computing 2002) and the (poly)logarithmic regret of UCB1 (Auer et al., Machine Learning 2002) for stochastic rewards. Adversarial rewards and stochastic rewards are the two main settings in the literature on (non-Bayesian) multi-armed bandits. Prior work on multi-armed bandits treats them separately, and does not attempt to jointly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.4473","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":"2026-05-18T04:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iMi3myyj1sNdURKvkNzvFPtfcLKvKxrvk130DDFrd0npVDFk8pzg1Q7UlaEUmVSXDRnVU5ailFEtBbAnXjsuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:50:49.041196Z"},"content_sha256":"84972c24b4257b974c135514007a42a2b62253863502abcd155232e676e13869","schema_version":"1.0","event_id":"sha256:84972c24b4257b974c135514007a42a2b62253863502abcd155232e676e13869"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPUR34BQNOUO4T3NNJL5EDKYOS/bundle.json","state_url":"https://pith.science/pith/QPUR34BQNOUO4T3NNJL5EDKYOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPUR34BQNOUO4T3NNJL5EDKYOS/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":"2026-06-12T08:50:49Z","links":{"resolver":"https://pith.science/pith/QPUR34BQNOUO4T3NNJL5EDKYOS","bundle":"https://pith.science/pith/QPUR34BQNOUO4T3NNJL5EDKYOS/bundle.json","state":"https://pith.science/pith/QPUR34BQNOUO4T3NNJL5EDKYOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPUR34BQNOUO4T3NNJL5EDKYOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:QPUR34BQNOUO4T3NNJL5EDKYOS","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":"d4cb119c3fa4578fdb877d9675f21a48872d0cff5a9145338b4783a510d93250","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-20T21:29:28Z","title_canon_sha256":"d17e972425e79573018db17269f848376225811db3a8b87be1f7a57dbb000942"},"schema_version":"1.0","source":{"id":"1202.4473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.4473","created_at":"2026-05-18T04:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"1202.4473v1","created_at":"2026-05-18T04:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.4473","created_at":"2026-05-18T04:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"QPUR34BQNOUO","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"QPUR34BQNOUO4T3N","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"QPUR34BQ","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:84972c24b4257b974c135514007a42a2b62253863502abcd155232e676e13869","target":"graph","created_at":"2026-05-18T04:01:50Z","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 present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifically, SAO combines the square-root worst-case regret of Exp3 (Auer et al., SIAM J. on Computing 2002) and the (poly)logarithmic regret of UCB1 (Auer et al., Machine Learning 2002) for stochastic rewards. Adversarial rewards and stochastic rewards are the two main settings in the literature on (non-Bayesian) multi-armed bandits. Prior work on multi-armed bandits treats them separately, and does not attempt to jointly ","authors_text":"Aleksandrs Slivkins, Sebastien Bubeck","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-20T21:29:28Z","title":"The best of both worlds: stochastic and adversarial bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.4473","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:f3b211cd4335f7b858cf80cc8119e997126251679587408f092e718dbbfc7620","target":"record","created_at":"2026-05-18T04:01:50Z","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":"d4cb119c3fa4578fdb877d9675f21a48872d0cff5a9145338b4783a510d93250","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-20T21:29:28Z","title_canon_sha256":"d17e972425e79573018db17269f848376225811db3a8b87be1f7a57dbb000942"},"schema_version":"1.0","source":{"id":"1202.4473","kind":"arxiv","version":1}},"canonical_sha256":"83e91df0306ba8ee4f6d6a57d20d58749db82e84f071bf42fc91159b0e7d0ae6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83e91df0306ba8ee4f6d6a57d20d58749db82e84f071bf42fc91159b0e7d0ae6","first_computed_at":"2026-05-18T04:01:50.556583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:01:50.556583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAcPoL+Esk6k/AjN1iM/H4zkB9XMD17Zy7sKIzvxby84CaWgfBat/mPLE5VSlI7uxwGeTb0IGQ5jTvn4F0NSCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:01:50.557022Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.4473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3b211cd4335f7b858cf80cc8119e997126251679587408f092e718dbbfc7620","sha256:84972c24b4257b974c135514007a42a2b62253863502abcd155232e676e13869"],"state_sha256":"050b3a7c571e0b3cf3c9baa32c093990d09ec49510c38e16ed55daab33668068"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BynDQJokNWwEW0abWq8AvAS/U0ADClFGhsAxmZFJCkQXhuj4+DAzs9xQQ5mf3rubM1NOeMUywZkQMs5La+rhDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T08:50:49.043540Z","bundle_sha256":"62bf7170f817e7d27a02b1b029e687f893bd1eab83e063e681514b6e411227c9"}}