{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KQQ6JBP3AINAEHC4GYKASSOMB7","short_pith_number":"pith:KQQ6JBP3","schema_version":"1.0","canonical_sha256":"5421e485fb021a021c5c36140949cc0fc90943d705767014bd82bc0e31409c7e","source":{"kind":"arxiv","id":"2605.29645","version":1},"attestation_state":"computed","paper":{"title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Alon Cohen, Fan Chen, Liad Erez, Shay Moran, Tomer Koren, Yishay Mansour","submitted_at":"2026-05-28T09:12:20Z","abstract_excerpt":"We study contextual bandits in the stochastic i.i.d.\\ setting, where a learner observes contexts drawn from an unknown distribution, selects actions from a finite set $A$, and aims to identify an approximately optimal policy from a given class based on bandit feedback. Motivated by bandit multiclass classification with zero-one rewards, we focus on the \\emph{$s$-sparse} setting in which, for every context, the reward vector has $L_1$-norm at most $s \\ll |A|$. Our main result is the design of algorithms that, with high probability, output an $\\epsilon$-optimal policy compared to policy class $\\"},"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":"2605.29645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T09:12:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5a7370f7028e23761d627644f16e1f0d8ffdde83b3c894101bf14419d0d04b81","abstract_canon_sha256":"a198d152eb9c0ac62d5b7c05b52a2b8842cbc3cd1641f6e2a946df9ce283ab13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:52.842362Z","signature_b64":"TEp67NtyMQT6gN//cXLB4aLRvMnnB64haEn/0CLVaQiSbHvdRGZPfaROmCaFa6rzb75Pu7pYaTljBxq85ZXlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5421e485fb021a021c5c36140949cc0fc90943d705767014bd82bc0e31409c7e","last_reissued_at":"2026-05-29T01:05:52.841818Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:52.841818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Alon Cohen, Fan Chen, Liad Erez, Shay Moran, Tomer Koren, Yishay Mansour","submitted_at":"2026-05-28T09:12:20Z","abstract_excerpt":"We study contextual bandits in the stochastic i.i.d.\\ setting, where a learner observes contexts drawn from an unknown distribution, selects actions from a finite set $A$, and aims to identify an approximately optimal policy from a given class based on bandit feedback. Motivated by bandit multiclass classification with zero-one rewards, we focus on the \\emph{$s$-sparse} setting in which, for every context, the reward vector has $L_1$-norm at most $s \\ll |A|$. Our main result is the design of algorithms that, with high probability, output an $\\epsilon$-optimal policy compared to policy class $\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29645","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/2605.29645/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.29645","created_at":"2026-05-29T01:05:52.841891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29645v1","created_at":"2026-05-29T01:05:52.841891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29645","created_at":"2026-05-29T01:05:52.841891+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQQ6JBP3AINA","created_at":"2026-05-29T01:05:52.841891+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQQ6JBP3AINAEHC4","created_at":"2026-05-29T01:05:52.841891+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQQ6JBP3","created_at":"2026-05-29T01:05:52.841891+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/KQQ6JBP3AINAEHC4GYKASSOMB7","json":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7.json","graph_json":"https://pith.science/api/pith-number/KQQ6JBP3AINAEHC4GYKASSOMB7/graph.json","events_json":"https://pith.science/api/pith-number/KQQ6JBP3AINAEHC4GYKASSOMB7/events.json","paper":"https://pith.science/paper/KQQ6JBP3"},"agent_actions":{"view_html":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7","download_json":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7.json","view_paper":"https://pith.science/paper/KQQ6JBP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29645&json=true","fetch_graph":"https://pith.science/api/pith-number/KQQ6JBP3AINAEHC4GYKASSOMB7/graph.json","fetch_events":"https://pith.science/api/pith-number/KQQ6JBP3AINAEHC4GYKASSOMB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7/action/storage_attestation","attest_author":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7/action/author_attestation","sign_citation":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7/action/citation_signature","submit_replication":"https://pith.science/pith/KQQ6JBP3AINAEHC4GYKASSOMB7/action/replication_record"}},"created_at":"2026-05-29T01:05:52.841891+00:00","updated_at":"2026-05-29T01:05:52.841891+00:00"}