{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I56QEXGZLDLDAUYVJKEPUUHYCY","short_pith_number":"pith:I56QEXGZ","schema_version":"1.0","canonical_sha256":"477d025cd958d63053154a88fa50f8160bc059b9379e5ea4787eba8505ad360c","source":{"kind":"arxiv","id":"2211.02703","version":1},"attestation_state":"computed","paper":{"title":"Online Learning and Bandits with Queried Hints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Aditya Bhaskara, Kamesh Munagala, Kostas Kollias, Sreenivas Gollapudi, Sungjin Im","submitted_at":"2022-11-04T18:41:08Z","abstract_excerpt":"We consider the classic online learning and stochastic multi-armed bandit (MAB) problems, when at each step, the online policy can probe and find out which of a small number ($k$) of choices has better reward (or loss) before making its choice. In this model, we derive algorithms whose regret bounds have exponentially better dependence on the time horizon compared to the classic regret bounds. In particular, we show that probing with $k=2$ suffices to achieve time-independent regret bounds for online linear and convex optimization. The same number of probes improve the regret bound of stochast"},"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":"2211.02703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2022-11-04T18:41:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f093203e53255e893bdac17a0e30e72858a0c8c178442e9119b58f12310a7ce4","abstract_canon_sha256":"efe57f1579caf6aef11f2e14000637d51597e05af4baea05e80cc4e8d77b4b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:20.620755Z","signature_b64":"Tig6p/amPjErFRP5ZrYJ5/kLTwIioCSXATZyCqi0L6SbthXcszxn/BmTtqz11GYV31Wx7sb3Saaht6vidP7DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"477d025cd958d63053154a88fa50f8160bc059b9379e5ea4787eba8505ad360c","last_reissued_at":"2026-07-05T05:13:20.620251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:20.620251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning and Bandits with Queried Hints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Aditya Bhaskara, Kamesh Munagala, Kostas Kollias, Sreenivas Gollapudi, Sungjin Im","submitted_at":"2022-11-04T18:41:08Z","abstract_excerpt":"We consider the classic online learning and stochastic multi-armed bandit (MAB) problems, when at each step, the online policy can probe and find out which of a small number ($k$) of choices has better reward (or loss) before making its choice. In this model, we derive algorithms whose regret bounds have exponentially better dependence on the time horizon compared to the classic regret bounds. In particular, we show that probing with $k=2$ suffices to achieve time-independent regret bounds for online linear and convex optimization. The same number of probes improve the regret bound of stochast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02703","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/2211.02703/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":"2211.02703","created_at":"2026-07-05T05:13:20.620312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02703v1","created_at":"2026-07-05T05:13:20.620312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02703","created_at":"2026-07-05T05:13:20.620312+00:00"},{"alias_kind":"pith_short_12","alias_value":"I56QEXGZLDLD","created_at":"2026-07-05T05:13:20.620312+00:00"},{"alias_kind":"pith_short_16","alias_value":"I56QEXGZLDLDAUYV","created_at":"2026-07-05T05:13:20.620312+00:00"},{"alias_kind":"pith_short_8","alias_value":"I56QEXGZ","created_at":"2026-07-05T05:13:20.620312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15812","citing_title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY","json":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY.json","graph_json":"https://pith.science/api/pith-number/I56QEXGZLDLDAUYVJKEPUUHYCY/graph.json","events_json":"https://pith.science/api/pith-number/I56QEXGZLDLDAUYVJKEPUUHYCY/events.json","paper":"https://pith.science/paper/I56QEXGZ"},"agent_actions":{"view_html":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY","download_json":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY.json","view_paper":"https://pith.science/paper/I56QEXGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02703&json=true","fetch_graph":"https://pith.science/api/pith-number/I56QEXGZLDLDAUYVJKEPUUHYCY/graph.json","fetch_events":"https://pith.science/api/pith-number/I56QEXGZLDLDAUYVJKEPUUHYCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY/action/storage_attestation","attest_author":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY/action/author_attestation","sign_citation":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY/action/citation_signature","submit_replication":"https://pith.science/pith/I56QEXGZLDLDAUYVJKEPUUHYCY/action/replication_record"}},"created_at":"2026-07-05T05:13:20.620312+00:00","updated_at":"2026-07-05T05:13:20.620312+00:00"}