{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BA5XDTTSAQBO4J5JROXASYKFKK","short_pith_number":"pith:BA5XDTTS","canonical_record":{"source":{"id":"2303.05606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T22:16:28Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"535ed8d63f0ce946b79b51a35386f5697ea30c6dce88c73b050dc5ddb1737201","abstract_canon_sha256":"a916f7c573b704c448855f210ae69a0301b2fafb83f8768d10ed7e0c3f6611ca"},"schema_version":"1.0"},"canonical_sha256":"083b71ce720402ee27a98bae0961455293b1ed1aa042e08ec16635b8a1ab3652","source":{"kind":"arxiv","id":"2303.05606","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BA5XDTTSAQBO4J5JROXASYKFKK","target":"record","payload":{"canonical_record":{"source":{"id":"2303.05606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T22:16:28Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"535ed8d63f0ce946b79b51a35386f5697ea30c6dce88c73b050dc5ddb1737201","abstract_canon_sha256":"a916f7c573b704c448855f210ae69a0301b2fafb83f8768d10ed7e0c3f6611ca"},"schema_version":"1.0"},"canonical_sha256":"083b71ce720402ee27a98bae0961455293b1ed1aa042e08ec16635b8a1ab3652","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:04.328226Z","signature_b64":"q+Q4aqyPzEmyP8Okha7kG1ydSNKlOVb2yIOu5/zc0cW2iQenCRLKzyTF7WDshHZT24cdQ0af63F04Phze7LCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"083b71ce720402ee27a98bae0961455293b1ed1aa042e08ec16635b8a1ab3652","last_reissued_at":"2026-07-05T05:51:04.327768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:04.327768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.05606","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zk1DGQrVIArANz0VfaABLDMIpWO/e0/cGdHcL5pR2gqCTw7MkjtXvhWkZvS57UUuVWIebn7BQ0K7lXQfHXz0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:50:02.278002Z"},"content_sha256":"fc0375a29aa17782c0c46ab16925878f52506f0dafcff0af71a58db91324f4f0","schema_version":"1.0","event_id":"sha256:fc0375a29aa17782c0c46ab16925878f52506f0dafcff0af71a58db91324f4f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BA5XDTTSAQBO4J5JROXASYKFKK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Qiang Sun, Xiang Li","submitted_at":"2023-03-09T22:16:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05606","kind":"arxiv","version":2},"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/2303.05606/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPZJxgCHkY9WwuyrIiBA+7MYsuslSHzhycIPD/FqGuC8eJUA6h8H1c7fZC4Xwv2MV38SJ9XCUUIo0CUi3/4FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:50:02.278747Z"},"content_sha256":"b8f00025e964d7e7e655e7675f2689a5ea8aa825e14783483095c07a5396e10b","schema_version":"1.0","event_id":"sha256:b8f00025e964d7e7e655e7675f2689a5ea8aa825e14783483095c07a5396e10b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BA5XDTTSAQBO4J5JROXASYKFKK/bundle.json","state_url":"https://pith.science/pith/BA5XDTTSAQBO4J5JROXASYKFKK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BA5XDTTSAQBO4J5JROXASYKFKK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T07:50:02Z","links":{"resolver":"https://pith.science/pith/BA5XDTTSAQBO4J5JROXASYKFKK","bundle":"https://pith.science/pith/BA5XDTTSAQBO4J5JROXASYKFKK/bundle.json","state":"https://pith.science/pith/BA5XDTTSAQBO4J5JROXASYKFKK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BA5XDTTSAQBO4J5JROXASYKFKK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2S17DV3SYJ7ITT5onwamEylG5bw7kpBeki+sMWvhiR5cmT7/L23sP7Z6i/4FnuXtBN901f6ilx/M72U3IO9Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:50:02.285839Z","bundle_sha256":"dd29842a58c61225ecab19eb40f2ee2c7fbca84a54812c95d9b43da303b5b864"}}