{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FB2MPSDJQF3EAZQSAM4RRX4AXP","short_pith_number":"pith:FB2MPSDJ","schema_version":"1.0","canonical_sha256":"2874c7c8698176406612033918df80bbe0eec3f8e6c0fef15a3eef91cd71eeb8","source":{"kind":"arxiv","id":"2102.07800","version":1},"attestation_state":"computed","paper":{"title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Rakhlin, Daniel Hill, Dean Foster, Inderjit Dhillon, Lexing Ying, Rahul Kidambi, Rajat Sen","submitted_at":"2021-02-15T19:10:52Z","abstract_excerpt":"Motivated by modern applications, such as online advertisement and recommender systems, we study the top-$k$ extreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select $k$ arms and observe all or some of the rewards for the chosen arms. We first propose an algorithm for the non-extreme realizable setting, utilizing the Inverse Gap Weighting strategy for selecting multiple arms. We show that our algorithm has a regret guarantee of $O(k\\sqrt{(A-k+1)T \\log (|\\mathcal{F}|T)})$, where $A$ is the total number of arms and $\\mathcal{F}$ is "},"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":"2102.07800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-15T19:10:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d52d159260c6f33b78665bdf99195f91044ae2a9ae8659839a5bce0c1e06598","abstract_canon_sha256":"001408229e7b436cf9fe6f0757a0fc8037f7838d12f777a026bd7c93de8ec5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:43.512263Z","signature_b64":"b3JnS90/DDJUOde/oIHDsrcadf8wCeZs33IDHMc9VFu1zoBrNZxjrZcFNZQH/5JYk3JvELEm584c4+uKh1tLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2874c7c8698176406612033918df80bbe0eec3f8e6c0fef15a3eef91cd71eeb8","last_reissued_at":"2026-07-05T02:15:43.511814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:43.511814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Rakhlin, Daniel Hill, Dean Foster, Inderjit Dhillon, Lexing Ying, Rahul Kidambi, Rajat Sen","submitted_at":"2021-02-15T19:10:52Z","abstract_excerpt":"Motivated by modern applications, such as online advertisement and recommender systems, we study the top-$k$ extreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select $k$ arms and observe all or some of the rewards for the chosen arms. We first propose an algorithm for the non-extreme realizable setting, utilizing the Inverse Gap Weighting strategy for selecting multiple arms. We show that our algorithm has a regret guarantee of $O(k\\sqrt{(A-k+1)T \\log (|\\mathcal{F}|T)})$, where $A$ is the total number of arms and $\\mathcal{F}$ is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07800","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/2102.07800/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":"2102.07800","created_at":"2026-07-05T02:15:43.511881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07800v1","created_at":"2026-07-05T02:15:43.511881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07800","created_at":"2026-07-05T02:15:43.511881+00:00"},{"alias_kind":"pith_short_12","alias_value":"FB2MPSDJQF3E","created_at":"2026-07-05T02:15:43.511881+00:00"},{"alias_kind":"pith_short_16","alias_value":"FB2MPSDJQF3EAZQS","created_at":"2026-07-05T02:15:43.511881+00:00"},{"alias_kind":"pith_short_8","alias_value":"FB2MPSDJ","created_at":"2026-07-05T02:15:43.511881+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/FB2MPSDJQF3EAZQSAM4RRX4AXP","json":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP.json","graph_json":"https://pith.science/api/pith-number/FB2MPSDJQF3EAZQSAM4RRX4AXP/graph.json","events_json":"https://pith.science/api/pith-number/FB2MPSDJQF3EAZQSAM4RRX4AXP/events.json","paper":"https://pith.science/paper/FB2MPSDJ"},"agent_actions":{"view_html":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP","download_json":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP.json","view_paper":"https://pith.science/paper/FB2MPSDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07800&json=true","fetch_graph":"https://pith.science/api/pith-number/FB2MPSDJQF3EAZQSAM4RRX4AXP/graph.json","fetch_events":"https://pith.science/api/pith-number/FB2MPSDJQF3EAZQSAM4RRX4AXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP/action/storage_attestation","attest_author":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP/action/author_attestation","sign_citation":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP/action/citation_signature","submit_replication":"https://pith.science/pith/FB2MPSDJQF3EAZQSAM4RRX4AXP/action/replication_record"}},"created_at":"2026-07-05T02:15:43.511881+00:00","updated_at":"2026-07-05T02:15:43.511881+00:00"}