{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2S3LLRXGQSCKBNESZA4JYP7DHT","short_pith_number":"pith:2S3LLRXG","schema_version":"1.0","canonical_sha256":"d4b6b5c6e68484a0b492c8389c3fe33ce268a4ba2d3b62f572fb35a2e7bd5bee","source":{"kind":"arxiv","id":"1811.05154","version":3},"attestation_state":"computed","paper":{"title":"Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Sharan Vaswani, Tor Lattimore, Zheng Wen","submitted_at":"2018-11-13T08:15:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1811.05154","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T08:15:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"640ebca79643c3fa14ba7d0486da6131efd4b8f9dc452348af67652d7ada2690","abstract_canon_sha256":"0ba5b665c73ae751b4059961ae2beaebb8017dbe5454fd4c7aac89ee57ca2c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:48.764863Z","signature_b64":"tAiSKq/5AHTbCyTaRLfgpswRpWK3W5ZYdjhu/PqLkOrsE9yaRl9ZocV3cftkz6oxp7nrwM9vATbvZjv2gH4EDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4b6b5c6e68484a0b492c8389c3fe33ce268a4ba2d3b62f572fb35a2e7bd5bee","last_reissued_at":"2026-05-17T23:42:48.764182Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:48.764182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Sharan Vaswani, Tor Lattimore, Zheng Wen","submitted_at":"2018-11-13T08:15:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05154","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.05154","created_at":"2026-05-17T23:42:48.764278+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.05154v3","created_at":"2026-05-17T23:42:48.764278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05154","created_at":"2026-05-17T23:42:48.764278+00:00"},{"alias_kind":"pith_short_12","alias_value":"2S3LLRXGQSCK","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2S3LLRXGQSCKBNES","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2S3LLRXG","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT","json":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT.json","graph_json":"https://pith.science/api/pith-number/2S3LLRXGQSCKBNESZA4JYP7DHT/graph.json","events_json":"https://pith.science/api/pith-number/2S3LLRXGQSCKBNESZA4JYP7DHT/events.json","paper":"https://pith.science/paper/2S3LLRXG"},"agent_actions":{"view_html":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT","download_json":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT.json","view_paper":"https://pith.science/paper/2S3LLRXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.05154&json=true","fetch_graph":"https://pith.science/api/pith-number/2S3LLRXGQSCKBNESZA4JYP7DHT/graph.json","fetch_events":"https://pith.science/api/pith-number/2S3LLRXGQSCKBNESZA4JYP7DHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT/action/storage_attestation","attest_author":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT/action/author_attestation","sign_citation":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT/action/citation_signature","submit_replication":"https://pith.science/pith/2S3LLRXGQSCKBNESZA4JYP7DHT/action/replication_record"}},"created_at":"2026-05-17T23:42:48.764278+00:00","updated_at":"2026-05-17T23:42:48.764278+00:00"}