{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BA5XDTTSAQBO4J5JROXASYKFKK","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":"a916f7c573b704c448855f210ae69a0301b2fafb83f8768d10ed7e0c3f6611ca","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T22:16:28Z","title_canon_sha256":"535ed8d63f0ce946b79b51a35386f5697ea30c6dce88c73b050dc5ddb1737201"},"schema_version":"1.0","source":{"id":"2303.05606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05606","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05606v2","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05606","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"BA5XDTTSAQBO","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_16","alias_value":"BA5XDTTSAQBO4J5J","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_8","alias_value":"BA5XDTTS","created_at":"2026-07-05T05:51:04Z"}],"graph_snapshots":[{"event_id":"sha256:b8f00025e964d7e7e655e7675f2689a5ea8aa825e14783483095c07a5396e10b","target":"graph","created_at":"2026-07-05T05:51:04Z","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/2303.05606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents two algorithms, AdaOFUL and VARA, for online sequential decision-making in the presence of heavy-tailed rewards with only finite variances. For linear stochastic bandits, we address the issue of heavy-tailed rewards by modifying the adaptive Huber regression and proposing AdaOFUL. AdaOFUL achieves a state-of-the-art regret bound of $\\widetilde{O}\\big(d\\big(\\sum_{t=1}^T \\nu_{t}^2\\big)^{1/2}+d\\big)$ as if the rewards were uniformly bounded, where $\\nu_{t}^2$ is the observed conditional variance of the reward at round $t$, $d$ is the feature dimension, and $\\widetilde{O}(\\cdot","authors_text":"Qiang Sun, Xiang Li","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T22:16:28Z","title":"Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05606","kind":"arxiv","version":2},"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:fc0375a29aa17782c0c46ab16925878f52506f0dafcff0af71a58db91324f4f0","target":"record","created_at":"2026-07-05T05:51:04Z","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":"a916f7c573b704c448855f210ae69a0301b2fafb83f8768d10ed7e0c3f6611ca","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T22:16:28Z","title_canon_sha256":"535ed8d63f0ce946b79b51a35386f5697ea30c6dce88c73b050dc5ddb1737201"},"schema_version":"1.0","source":{"id":"2303.05606","kind":"arxiv","version":2}},"canonical_sha256":"083b71ce720402ee27a98bae0961455293b1ed1aa042e08ec16635b8a1ab3652","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"083b71ce720402ee27a98bae0961455293b1ed1aa042e08ec16635b8a1ab3652","first_computed_at":"2026-07-05T05:51:04.327768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:04.327768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q+Q4aqyPzEmyP8Okha7kG1ydSNKlOVb2yIOu5/zc0cW2iQenCRLKzyTF7WDshHZT24cdQ0af63F04Phze7LCDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:04.328226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.05606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc0375a29aa17782c0c46ab16925878f52506f0dafcff0af71a58db91324f4f0","sha256:b8f00025e964d7e7e655e7675f2689a5ea8aa825e14783483095c07a5396e10b"],"state_sha256":"2479e161740ce9eeac91f933180561621afe69c0ecb2c3a7e8a9fe6e2567a14c"}