{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QWXH4H2BFTLDMCUIB76VSWCQHZ","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":"d44c0b757f3df4490a6da09e6eabcb7fde64236492bdccb15739fecd13a35627","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-26T18:04:58Z","title_canon_sha256":"63f94b9f6caa83ffc19dd0f4f6456a0187d93232da3a1650721f1b48c5e755ff"},"schema_version":"1.0","source":{"id":"1902.10089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10089","created_at":"2026-07-05T00:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10089v2","created_at":"2026-07-05T00:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10089","created_at":"2026-07-05T00:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"QWXH4H2BFTLD","created_at":"2026-07-05T00:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"QWXH4H2BFTLDMCUI","created_at":"2026-07-05T00:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"QWXH4H2B","created_at":"2026-07-05T00:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:7c39136c69255c1f72e8d0cb805a05313cff668be236ddbdc6ea3c67dd33ed90","target":"graph","created_at":"2026-07-05T00:17:00Z","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/1902.10089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an online algorithm for cumulative regret minimization in a stochastic multi-armed bandit. The algorithm adds $O(t)$ i.i.d. pseudo-rewards to its history in round $t$ and then pulls the arm with the highest average reward in its perturbed history. Therefore, we call it perturbed-history exploration (PHE). The pseudo-rewards are carefully designed to offset potentially underestimated mean rewards of arms with a high probability. We derive near-optimal gap-dependent and gap-free bounds on the $n$-round regret of PHE. The key step in our analysis is a novel argument that shows that ran","authors_text":"Branislav Kveton, Craig Boutilier, Csaba Szepesvari, Mohammad Ghavamzadeh","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-26T18:04:58Z","title":"Perturbed-History Exploration in Stochastic Multi-Armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10089","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:cac47503936ca4b16d3e54db52a4295f4ac2fbc91fb1e2657e1317101d3a3a45","target":"record","created_at":"2026-07-05T00:17:00Z","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":"d44c0b757f3df4490a6da09e6eabcb7fde64236492bdccb15739fecd13a35627","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-26T18:04:58Z","title_canon_sha256":"63f94b9f6caa83ffc19dd0f4f6456a0187d93232da3a1650721f1b48c5e755ff"},"schema_version":"1.0","source":{"id":"1902.10089","kind":"arxiv","version":2}},"canonical_sha256":"85ae7e1f412cd6360a880ffd5958503e4c5c308b1d0d3847ee1c331441f9110c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85ae7e1f412cd6360a880ffd5958503e4c5c308b1d0d3847ee1c331441f9110c","first_computed_at":"2026-07-05T00:17:00.886254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:17:00.886254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xRiTWM8P2qB2a0cL++U9N7nojJL+Kd9fYlue5oJG3Muqu9nPNn2yZTgiRIzX2W554v7G0P89sDhlabgbfYN4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:17:00.886884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cac47503936ca4b16d3e54db52a4295f4ac2fbc91fb1e2657e1317101d3a3a45","sha256:7c39136c69255c1f72e8d0cb805a05313cff668be236ddbdc6ea3c67dd33ed90"],"state_sha256":"6f301d79d9c7d56710ee231cbb96e588c2423eb1c7e7a05800bc25fcec3d1494"}