{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FG5JC3IAVMNGEX7GAN6YZLFTKV","short_pith_number":"pith:FG5JC3IA","schema_version":"1.0","canonical_sha256":"29ba916d00ab1a625fe6037d8cacb35569a20757594ec853dc599095d5165cc1","source":{"kind":"arxiv","id":"2010.03104","version":1},"attestation_state":"computed","paper":{"title":"Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, David Simchi-Levi, Dylan J. Foster, Yunzong Xu","submitted_at":"2020-10-07T01:33:06Z","abstract_excerpt":"In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on \"easy\" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While positive results are known for certain special cases, there is no general theory characterizing when and how instance-dependent regret bounds for contextual bandits can be achieved for rich, general classes of policies. We introduce a family of complexity measures that are both sufficient and necessary to obtain instance-dependent regret bounds. We then introduce n"},"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":"2010.03104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T01:33:06Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"3289b635d81ad899cea83da3924cb842deaed5673de06de9ac9fa9c4c7f93680","abstract_canon_sha256":"293bc2ab08618c44a66a4cd641647d6a717e03846cc5bad715f56b2ee9944704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:59.775975Z","signature_b64":"DNU79mQ+LdWAdfC5rvaCSQuaQ5D3Qm7dd6N1Q02bJJowD8Df2G07OMPMAIaeOcPfU2KLIf8Qcs1DmbyOcLpFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ba916d00ab1a625fe6037d8cacb35569a20757594ec853dc599095d5165cc1","last_reissued_at":"2026-07-05T01:40:59.775510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:59.775510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, David Simchi-Levi, Dylan J. Foster, Yunzong Xu","submitted_at":"2020-10-07T01:33:06Z","abstract_excerpt":"In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on \"easy\" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While positive results are known for certain special cases, there is no general theory characterizing when and how instance-dependent regret bounds for contextual bandits can be achieved for rich, general classes of policies. We introduce a family of complexity measures that are both sufficient and necessary to obtain instance-dependent regret bounds. We then introduce n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03104","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/2010.03104/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":"2010.03104","created_at":"2026-07-05T01:40:59.775563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03104v1","created_at":"2026-07-05T01:40:59.775563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03104","created_at":"2026-07-05T01:40:59.775563+00:00"},{"alias_kind":"pith_short_12","alias_value":"FG5JC3IAVMNG","created_at":"2026-07-05T01:40:59.775563+00:00"},{"alias_kind":"pith_short_16","alias_value":"FG5JC3IAVMNGEX7G","created_at":"2026-07-05T01:40:59.775563+00:00"},{"alias_kind":"pith_short_8","alias_value":"FG5JC3IA","created_at":"2026-07-05T01:40:59.775563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29645","citing_title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV","json":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV.json","graph_json":"https://pith.science/api/pith-number/FG5JC3IAVMNGEX7GAN6YZLFTKV/graph.json","events_json":"https://pith.science/api/pith-number/FG5JC3IAVMNGEX7GAN6YZLFTKV/events.json","paper":"https://pith.science/paper/FG5JC3IA"},"agent_actions":{"view_html":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV","download_json":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV.json","view_paper":"https://pith.science/paper/FG5JC3IA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03104&json=true","fetch_graph":"https://pith.science/api/pith-number/FG5JC3IAVMNGEX7GAN6YZLFTKV/graph.json","fetch_events":"https://pith.science/api/pith-number/FG5JC3IAVMNGEX7GAN6YZLFTKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV/action/storage_attestation","attest_author":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV/action/author_attestation","sign_citation":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV/action/citation_signature","submit_replication":"https://pith.science/pith/FG5JC3IAVMNGEX7GAN6YZLFTKV/action/replication_record"}},"created_at":"2026-07-05T01:40:59.775563+00:00","updated_at":"2026-07-05T01:40:59.775563+00:00"}