{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ON3AYS6CGXVYC5DVCMVAEPT7C4","short_pith_number":"pith:ON3AYS6C","schema_version":"1.0","canonical_sha256":"73760c4bc235eb817475132a023e7f171312d0fa87a11096dfdbea92954f73fd","source":{"kind":"arxiv","id":"2003.01922","version":2},"attestation_state":"computed","paper":{"title":"Taking a hint: How to leverage loss predictors in contextual bandits?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Chen-Yu Wei, Haipeng Luo","submitted_at":"2020-03-04T07:36:38Z","abstract_excerpt":"We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\\mathcal{O}(\\sqrt{T})$ for learning over $T$ rounds, when the total error of the predictor $\\mathcal{E} \\leq T$ is relatively small. We provide a complete answer to this question, including upper and lower bounds for various settings: adversarial versus stochastic environments, known versus unknown $\\mathcal{E}$, and single versus multiple predictors. We show several surprising results, such as 1) the optimal regret is $\\math"},"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":"2003.01922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T07:36:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c559e1fa9fd78e24064d98373dc720f4d9021c3300445764e88708a4fe8e468c","abstract_canon_sha256":"963d521159594cc1cc209f9a4a5ee07c28838b3772cb1da535458c55615e39a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:14.207117Z","signature_b64":"n2PpzzAMPSZMJosDAPkdxKvxeo8eAfD2WLPr55i9YcrR0y6UT9L+dSHMfwOMC/sxeGTPNPpa7bq555+F5kpoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73760c4bc235eb817475132a023e7f171312d0fa87a11096dfdbea92954f73fd","last_reissued_at":"2026-07-05T01:43:14.206664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:14.206664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taking a hint: How to leverage loss predictors in contextual bandits?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Chen-Yu Wei, Haipeng Luo","submitted_at":"2020-03-04T07:36:38Z","abstract_excerpt":"We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\\mathcal{O}(\\sqrt{T})$ for learning over $T$ rounds, when the total error of the predictor $\\mathcal{E} \\leq T$ is relatively small. We provide a complete answer to this question, including upper and lower bounds for various settings: adversarial versus stochastic environments, known versus unknown $\\mathcal{E}$, and single versus multiple predictors. We show several surprising results, such as 1) the optimal regret is $\\math"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01922","kind":"arxiv","version":2},"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/2003.01922/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":"2003.01922","created_at":"2026-07-05T01:43:14.206717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.01922v2","created_at":"2026-07-05T01:43:14.206717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01922","created_at":"2026-07-05T01:43:14.206717+00:00"},{"alias_kind":"pith_short_12","alias_value":"ON3AYS6CGXVY","created_at":"2026-07-05T01:43:14.206717+00:00"},{"alias_kind":"pith_short_16","alias_value":"ON3AYS6CGXVYC5DV","created_at":"2026-07-05T01:43:14.206717+00:00"},{"alias_kind":"pith_short_8","alias_value":"ON3AYS6C","created_at":"2026-07-05T01:43:14.206717+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/ON3AYS6CGXVYC5DVCMVAEPT7C4","json":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4.json","graph_json":"https://pith.science/api/pith-number/ON3AYS6CGXVYC5DVCMVAEPT7C4/graph.json","events_json":"https://pith.science/api/pith-number/ON3AYS6CGXVYC5DVCMVAEPT7C4/events.json","paper":"https://pith.science/paper/ON3AYS6C"},"agent_actions":{"view_html":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4","download_json":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4.json","view_paper":"https://pith.science/paper/ON3AYS6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.01922&json=true","fetch_graph":"https://pith.science/api/pith-number/ON3AYS6CGXVYC5DVCMVAEPT7C4/graph.json","fetch_events":"https://pith.science/api/pith-number/ON3AYS6CGXVYC5DVCMVAEPT7C4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4/action/storage_attestation","attest_author":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4/action/author_attestation","sign_citation":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4/action/citation_signature","submit_replication":"https://pith.science/pith/ON3AYS6CGXVYC5DVCMVAEPT7C4/action/replication_record"}},"created_at":"2026-07-05T01:43:14.206717+00:00","updated_at":"2026-07-05T01:43:14.206717+00:00"}