{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YR5MZLPQKWMQKY5VQYILZBLHCM","short_pith_number":"pith:YR5MZLPQ","schema_version":"1.0","canonical_sha256":"c47accadf055990563b58610bc856713082f8285cf2180c3bb9a5cee6a7d9781","source":{"kind":"arxiv","id":"2203.12577","version":3},"attestation_state":"computed","paper":{"title":"Minimax Regret for Cascading Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Vial, R. Srikant, Sanjay Shakkottai, Sujay Sanghavi","submitted_at":"2022-03-23T17:37:43Z","abstract_excerpt":"Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting. For the case of unstructured rewards, we prove matching upper and lower bounds for the problem-independent (i.e., gap-free) regret, both of which strictly improve the best known. A key observation is that the hard instances of this problem are those with small mean rewards, i.e., the small click-through rates that are most relevant in practice. Based on this, and the fact that small mean implies small variance for Bernoullis, our key technical result show"},"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":"2203.12577","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-23T17:37:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a87f23f1070d0716aba35270a837d35e597ff247b0287c4f1b8883adbbb6cc26","abstract_canon_sha256":"2750bf028370d8d429fc04df55f1f1ab8e570e7f68dec04098e4a1e9da3f69fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:47.464459Z","signature_b64":"/mjiQPbM5GNVVKzTZiy86pRBF6yRBihf4zccIMNyHzuruD7qBVOaDXIobH8DNaqHzR9k6mW5/zgYNDxER5x5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c47accadf055990563b58610bc856713082f8285cf2180c3bb9a5cee6a7d9781","last_reissued_at":"2026-07-05T05:04:47.463956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:47.463956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax Regret for Cascading Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Vial, R. Srikant, Sanjay Shakkottai, Sujay Sanghavi","submitted_at":"2022-03-23T17:37:43Z","abstract_excerpt":"Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting. For the case of unstructured rewards, we prove matching upper and lower bounds for the problem-independent (i.e., gap-free) regret, both of which strictly improve the best known. A key observation is that the hard instances of this problem are those with small mean rewards, i.e., the small click-through rates that are most relevant in practice. Based on this, and the fact that small mean implies small variance for Bernoullis, our key technical result show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12577","kind":"arxiv","version":3},"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/2203.12577/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":"2203.12577","created_at":"2026-07-05T05:04:47.464016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12577v3","created_at":"2026-07-05T05:04:47.464016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12577","created_at":"2026-07-05T05:04:47.464016+00:00"},{"alias_kind":"pith_short_12","alias_value":"YR5MZLPQKWMQ","created_at":"2026-07-05T05:04:47.464016+00:00"},{"alias_kind":"pith_short_16","alias_value":"YR5MZLPQKWMQKY5V","created_at":"2026-07-05T05:04:47.464016+00:00"},{"alias_kind":"pith_short_8","alias_value":"YR5MZLPQ","created_at":"2026-07-05T05:04:47.464016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08077","citing_title":"Cascading Bandits Robust to Adversarial Corruptions","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM","json":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM.json","graph_json":"https://pith.science/api/pith-number/YR5MZLPQKWMQKY5VQYILZBLHCM/graph.json","events_json":"https://pith.science/api/pith-number/YR5MZLPQKWMQKY5VQYILZBLHCM/events.json","paper":"https://pith.science/paper/YR5MZLPQ"},"agent_actions":{"view_html":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM","download_json":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM.json","view_paper":"https://pith.science/paper/YR5MZLPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12577&json=true","fetch_graph":"https://pith.science/api/pith-number/YR5MZLPQKWMQKY5VQYILZBLHCM/graph.json","fetch_events":"https://pith.science/api/pith-number/YR5MZLPQKWMQKY5VQYILZBLHCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM/action/storage_attestation","attest_author":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM/action/author_attestation","sign_citation":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM/action/citation_signature","submit_replication":"https://pith.science/pith/YR5MZLPQKWMQKY5VQYILZBLHCM/action/replication_record"}},"created_at":"2026-07-05T05:04:47.464016+00:00","updated_at":"2026-07-05T05:04:47.464016+00:00"}