{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FVDKO3PYZP2KNZWCAYJMZAGTCW","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":"7fef492109580c168e664b96e47dbfd5a8f2cf980d5c5d5569f76c2b3a7dc9e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-29T18:57:52Z","title_canon_sha256":"e17a06bdd67e1c6ebd9dfb17d22e07b56a57795bdebbd0ddbbd4cbf395959aa6"},"schema_version":"1.0","source":{"id":"2101.12745","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.12745","created_at":"2026-07-05T03:26:58Z"},{"alias_kind":"arxiv_version","alias_value":"2101.12745v4","created_at":"2026-07-05T03:26:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.12745","created_at":"2026-07-05T03:26:58Z"},{"alias_kind":"pith_short_12","alias_value":"FVDKO3PYZP2K","created_at":"2026-07-05T03:26:58Z"},{"alias_kind":"pith_short_16","alias_value":"FVDKO3PYZP2KNZWC","created_at":"2026-07-05T03:26:58Z"},{"alias_kind":"pith_short_8","alias_value":"FVDKO3PY","created_at":"2026-07-05T03:26:58Z"}],"graph_snapshots":[{"event_id":"sha256:7103c89c99ebdb45273180aee86699ecdc7b3d9e19792d4e4eab68ba891038cc","target":"graph","created_at":"2026-07-05T03:26:58Z","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/2101.12745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents new \\emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an $\\tilde{O}(poly(d)\\sqrt{1 + \\sum_{k=1}^{K}\\sigma_k^2})$ data-dependent regret bound, where $d$ is the feature dimension, $K$ is the number of rounds, and $\\sigma_k^2$ is the \\emph{unknown} variance of the reward at the $k$-th round. This is the first regret bound that only scales with the variance and the dimension but \\emph{no explicit polynomial dependency on $K$","authors_text":"Jiaqi Yang, Simon S. Du, Xiangyang Ji, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-29T18:57:52Z","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.12745","kind":"arxiv","version":4},"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:a0c4a129b35acd3ddb80e726e893b29d5899284e198e01f09e7546a989ce7db6","target":"record","created_at":"2026-07-05T03:26:58Z","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":"7fef492109580c168e664b96e47dbfd5a8f2cf980d5c5d5569f76c2b3a7dc9e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-29T18:57:52Z","title_canon_sha256":"e17a06bdd67e1c6ebd9dfb17d22e07b56a57795bdebbd0ddbbd4cbf395959aa6"},"schema_version":"1.0","source":{"id":"2101.12745","kind":"arxiv","version":4}},"canonical_sha256":"2d46a76df8cbf4a6e6c20612cc80d315b952e757bb9fd0800bbf9187ac47d31a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d46a76df8cbf4a6e6c20612cc80d315b952e757bb9fd0800bbf9187ac47d31a","first_computed_at":"2026-07-05T03:26:58.539296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:58.539296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ymgR36HYkMRFIEqS2Ok9OplnDPCY7bmqeOP6yolW0thV7E3WO5DC6hKP93/gUxWBo3713TzRGoeeemWOxWNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:58.539800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.12745","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0c4a129b35acd3ddb80e726e893b29d5899284e198e01f09e7546a989ce7db6","sha256:7103c89c99ebdb45273180aee86699ecdc7b3d9e19792d4e4eab68ba891038cc"],"state_sha256":"90d1ba66e6db58be1baa5a2cbb08eb44988717b0acafc770d734a61d380bcaa6"}