{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FG5JC3IAVMNGEX7GAN6YZLFTKV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"293bc2ab08618c44a66a4cd641647d6a717e03846cc5bad715f56b2ee9944704","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T01:33:06Z","title_canon_sha256":"3289b635d81ad899cea83da3924cb842deaed5673de06de9ac9fa9c4c7f93680"},"schema_version":"1.0","source":{"id":"2010.03104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03104","created_at":"2026-07-05T01:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03104v1","created_at":"2026-07-05T01:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03104","created_at":"2026-07-05T01:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"FG5JC3IAVMNG","created_at":"2026-07-05T01:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"FG5JC3IAVMNGEX7G","created_at":"2026-07-05T01:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"FG5JC3IA","created_at":"2026-07-05T01:40:59Z"}],"graph_snapshots":[{"event_id":"sha256:2f64c0d483aafb1a8b06d1dba1606d62db537cd488fd8144a9da87c7f7d3637a","target":"graph","created_at":"2026-07-05T01:40:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.03104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Rakhlin, David Simchi-Levi, Dylan J. Foster, Yunzong Xu","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T01:33:06Z","title":"Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03104","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf36438cd86e6c7258e571e7d2888e6084e038ed2b5e1eef765b582da1e1a97e","target":"record","created_at":"2026-07-05T01:40:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"293bc2ab08618c44a66a4cd641647d6a717e03846cc5bad715f56b2ee9944704","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T01:33:06Z","title_canon_sha256":"3289b635d81ad899cea83da3924cb842deaed5673de06de9ac9fa9c4c7f93680"},"schema_version":"1.0","source":{"id":"2010.03104","kind":"arxiv","version":1}},"canonical_sha256":"29ba916d00ab1a625fe6037d8cacb35569a20757594ec853dc599095d5165cc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29ba916d00ab1a625fe6037d8cacb35569a20757594ec853dc599095d5165cc1","first_computed_at":"2026-07-05T01:40:59.775510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:59.775510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DNU79mQ+LdWAdfC5rvaCSQuaQ5D3Qm7dd6N1Q02bJJowD8Df2G07OMPMAIaeOcPfU2KLIf8Qcs1DmbyOcLpFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:59.775975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf36438cd86e6c7258e571e7d2888e6084e038ed2b5e1eef765b582da1e1a97e","sha256:2f64c0d483aafb1a8b06d1dba1606d62db537cd488fd8144a9da87c7f7d3637a"],"state_sha256":"0e3367c52a43c14eae998c985cb413477563da3fa3778dbee983e305a7443ff6"}