{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MMLRPP3ELBJS33WG6JCO7AVHVW","short_pith_number":"pith:MMLRPP3E","schema_version":"1.0","canonical_sha256":"631717bf6458532deec6f244ef82a7ad87e630b7277176b8515e1bcbc3cbe6ca","source":{"kind":"arxiv","id":"1810.07371","version":2},"attestation_state":"computed","paper":{"title":"Simple Regret Minimization for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aniket Anand Deshmukh, Clayton Scott, James W. Cutler, Mark Moldwin, Srinagesh Sharma","submitted_at":"2018-10-17T03:17:26Z","abstract_excerpt":"There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side information that is predictive of the best arm. Simple regret minimization assumes that the learner only incurs regret after a pure exploration phase. In this work, we study simple regret minimization for contextual bandits. Motivated by applications where the learner has separate "},"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":"1810.07371","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-17T03:17:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"237f0ca78a756976b81eff2050795b02075f3c982cf643b71b8776f66b0408b8","abstract_canon_sha256":"b68c84fb64a949d43606c3f08f5b0afae5a2c1e965ed13d87e7d2fea1c11a440"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:53.026031Z","signature_b64":"4L+iAeCjoBsbc78rloOP4vsuVbLoYSV1Ehv8eQ9wKQn35dBUiCvOU7Itj9/HuZ4nc1ftJU5/Jz664MS1WOiQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631717bf6458532deec6f244ef82a7ad87e630b7277176b8515e1bcbc3cbe6ca","last_reissued_at":"2026-07-05T00:43:53.025542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:53.025542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Regret Minimization for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aniket Anand Deshmukh, Clayton Scott, James W. Cutler, Mark Moldwin, Srinagesh Sharma","submitted_at":"2018-10-17T03:17:26Z","abstract_excerpt":"There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side information that is predictive of the best arm. Simple regret minimization assumes that the learner only incurs regret after a pure exploration phase. In this work, we study simple regret minimization for contextual bandits. Motivated by applications where the learner has separate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07371","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/1810.07371/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":"1810.07371","created_at":"2026-07-05T00:43:53.025602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07371v2","created_at":"2026-07-05T00:43:53.025602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07371","created_at":"2026-07-05T00:43:53.025602+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMLRPP3ELBJS","created_at":"2026-07-05T00:43:53.025602+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMLRPP3ELBJS33WG","created_at":"2026-07-05T00:43:53.025602+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMLRPP3E","created_at":"2026-07-05T00:43:53.025602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24331","citing_title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24803","citing_title":"Active Learning for Stochastic Contextual Linear Bandits","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20040","citing_title":"Active Context Selection Improves Simple Regret in Contextual Bandits","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW","json":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW.json","graph_json":"https://pith.science/api/pith-number/MMLRPP3ELBJS33WG6JCO7AVHVW/graph.json","events_json":"https://pith.science/api/pith-number/MMLRPP3ELBJS33WG6JCO7AVHVW/events.json","paper":"https://pith.science/paper/MMLRPP3E"},"agent_actions":{"view_html":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW","download_json":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW.json","view_paper":"https://pith.science/paper/MMLRPP3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07371&json=true","fetch_graph":"https://pith.science/api/pith-number/MMLRPP3ELBJS33WG6JCO7AVHVW/graph.json","fetch_events":"https://pith.science/api/pith-number/MMLRPP3ELBJS33WG6JCO7AVHVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW/action/storage_attestation","attest_author":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW/action/author_attestation","sign_citation":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW/action/citation_signature","submit_replication":"https://pith.science/pith/MMLRPP3ELBJS33WG6JCO7AVHVW/action/replication_record"}},"created_at":"2026-07-05T00:43:53.025602+00:00","updated_at":"2026-07-05T00:43:53.025602+00:00"}