{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2S3LLRXGQSCKBNESZA4JYP7DHT","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":"0ba5b665c73ae751b4059961ae2beaebb8017dbe5454fd4c7aac89ee57ca2c80","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T08:15:39Z","title_canon_sha256":"640ebca79643c3fa14ba7d0486da6131efd4b8f9dc452348af67652d7ada2690"},"schema_version":"1.0","source":{"id":"1811.05154","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05154","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05154v3","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05154","created_at":"2026-05-17T23:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"2S3LLRXGQSCK","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2S3LLRXGQSCKBNES","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2S3LLRXG","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:0262f8dccff3e0871edc3597001008ce4b9ad7b858db0a5fd8ca3e4d5ee5517d","target":"graph","created_at":"2026-05-17T23:42:48Z","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 propose a bandit algorithm that explores by randomizing its history of rewards. Specifically, it pulls the arm with the highest mean reward in a non-parametric bootstrap sample of its history with pseudo rewards. We design the pseudo rewards such that the bootstrap mean is optimistic with a sufficiently high probability. We call our algorithm Giro, which stands for garbage in, reward out. We analyze Giro in a Bernoulli bandit and derive a $O(K \\Delta^{-1} \\log n)$ bound on its $n$-round regret, where $\\Delta$ is the difference in the expected rewards of the optimal and the best suboptimal a","authors_text":"Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Sharan Vaswani, Tor Lattimore, Zheng Wen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T08:15:39Z","title":"Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05154","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":"sha256:30535624d02d09842da7deb6d2bd3851d8d610678eb728308d862903419b90dc","target":"record","created_at":"2026-05-17T23:42:48Z","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":"0ba5b665c73ae751b4059961ae2beaebb8017dbe5454fd4c7aac89ee57ca2c80","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T08:15:39Z","title_canon_sha256":"640ebca79643c3fa14ba7d0486da6131efd4b8f9dc452348af67652d7ada2690"},"schema_version":"1.0","source":{"id":"1811.05154","kind":"arxiv","version":3}},"canonical_sha256":"d4b6b5c6e68484a0b492c8389c3fe33ce268a4ba2d3b62f572fb35a2e7bd5bee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4b6b5c6e68484a0b492c8389c3fe33ce268a4ba2d3b62f572fb35a2e7bd5bee","first_computed_at":"2026-05-17T23:42:48.764182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:48.764182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tAiSKq/5AHTbCyTaRLfgpswRpWK3W5ZYdjhu/PqLkOrsE9yaRl9ZocV3cftkz6oxp7nrwM9vATbvZjv2gH4EDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:48.764863Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05154","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30535624d02d09842da7deb6d2bd3851d8d610678eb728308d862903419b90dc","sha256:0262f8dccff3e0871edc3597001008ce4b9ad7b858db0a5fd8ca3e4d5ee5517d"],"state_sha256":"7a279c7eca82abb52537f6a45a7b094848ea565ac98d52c10ccff99c7dfa7240"}