{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FCIFGSUCVYKGPZ7H2PTYPFAS3Y","short_pith_number":"pith:FCIFGSUC","canonical_record":{"source":{"id":"2302.10371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T00:17:24Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"7df3cfeee3e8c0b57cb2140c0c46f233e8ab0c7c85c65d3430de09e53785fdcc","abstract_canon_sha256":"9c540c5943913ae4a30df3364add7a4f540c2d5896652c6860175181d5b225de"},"schema_version":"1.0"},"canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","source":{"kind":"arxiv","id":"2302.10371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10371","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10371v1","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10371","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"FCIFGSUCVYKG","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"FCIFGSUCVYKGPZ7H","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"FCIFGSUC","created_at":"2026-07-05T05:43:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FCIFGSUCVYKGPZ7H2PTYPFAS3Y","target":"record","payload":{"canonical_record":{"source":{"id":"2302.10371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T00:17:24Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"7df3cfeee3e8c0b57cb2140c0c46f233e8ab0c7c85c65d3430de09e53785fdcc","abstract_canon_sha256":"9c540c5943913ae4a30df3364add7a4f540c2d5896652c6860175181d5b225de"},"schema_version":"1.0"},"canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:38.468057Z","signature_b64":"KZz//h9lPZH9Q1o6ahOTPclt1Hs/Vqsh7yrarH+HCQJ38Pwl4edlHEsBP7b7rbwiyZXPLETprm6pf64ps/wNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","last_reissued_at":"2026-07-05T05:43:38.467522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:38.467522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.10371","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MmG6mOjUuJEKf0yuxOm9AIG/rA8YllTtWltzJP8aOa53tSBJ7cq6fyehaRqMmTeOZ8vWl0BLGgsdP0HMmjQRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:57:58.319214Z"},"content_sha256":"76d59901e7dbe3cc1e935f91a98066f57883f802a40094639829999b88450380","schema_version":"1.0","event_id":"sha256:76d59901e7dbe3cc1e935f91a98066f57883f802a40094639829999b88450380"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FCIFGSUCVYKGPZ7H2PTYPFAS3Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu, Tong Zhang","submitted_at":"2023-02-21T00:17:24Z","abstract_excerpt":"Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime and the deterministic reward regime. However, these algorithms are either computationally intractable or unable to handle unknown variance of the noise. In this paper, we present a novel solution to this open problem by proposing the first computationally efficient algorithm for linear bandits with heteroscedastic noise. Our algorithm is adaptive to the unkno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10371","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/2302.10371/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":"2026-07-05T05:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0iZLEyUnDNkaSD141H9tBTI52RLhadWjnRWTlvR9qx9RE6c/AotFDs3UCi0SokYUX+/sVGqFqFY7H7ZHieUSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:57:58.319867Z"},"content_sha256":"afd0a31be5a7d5633a2c6cc4c71cce9ab0c4bcfe63c619dd1e63f9ba02acae85","schema_version":"1.0","event_id":"sha256:afd0a31be5a7d5633a2c6cc4c71cce9ab0c4bcfe63c619dd1e63f9ba02acae85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/bundle.json","state_url":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/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":"2026-07-07T04:57:58Z","links":{"resolver":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y","bundle":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/bundle.json","state":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FCIFGSUCVYKGPZ7H2PTYPFAS3Y","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":"9c540c5943913ae4a30df3364add7a4f540c2d5896652c6860175181d5b225de","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T00:17:24Z","title_canon_sha256":"7df3cfeee3e8c0b57cb2140c0c46f233e8ab0c7c85c65d3430de09e53785fdcc"},"schema_version":"1.0","source":{"id":"2302.10371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10371","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10371v1","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10371","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"FCIFGSUCVYKG","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"pith_short_16","alias_value":"FCIFGSUCVYKGPZ7H","created_at":"2026-07-05T05:43:38Z"},{"alias_kind":"pith_short_8","alias_value":"FCIFGSUC","created_at":"2026-07-05T05:43:38Z"}],"graph_snapshots":[{"event_id":"sha256:afd0a31be5a7d5633a2c6cc4c71cce9ab0c4bcfe63c619dd1e63f9ba02acae85","target":"graph","created_at":"2026-07-05T05:43:38Z","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/2302.10371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime and the deterministic reward regime. However, these algorithms are either computationally intractable or unable to handle unknown variance of the noise. In this paper, we present a novel solution to this open problem by proposing the first computationally efficient algorithm for linear bandits with heteroscedastic noise. Our algorithm is adaptive to the unkno","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu, Tong Zhang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T00:17:24Z","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10371","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":"sha256:76d59901e7dbe3cc1e935f91a98066f57883f802a40094639829999b88450380","target":"record","created_at":"2026-07-05T05:43:38Z","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":"9c540c5943913ae4a30df3364add7a4f540c2d5896652c6860175181d5b225de","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T00:17:24Z","title_canon_sha256":"7df3cfeee3e8c0b57cb2140c0c46f233e8ab0c7c85c65d3430de09e53785fdcc"},"schema_version":"1.0","source":{"id":"2302.10371","kind":"arxiv","version":1}},"canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","first_computed_at":"2026-07-05T05:43:38.467522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:38.467522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KZz//h9lPZH9Q1o6ahOTPclt1Hs/Vqsh7yrarH+HCQJ38Pwl4edlHEsBP7b7rbwiyZXPLETprm6pf64ps/wNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:38.468057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76d59901e7dbe3cc1e935f91a98066f57883f802a40094639829999b88450380","sha256:afd0a31be5a7d5633a2c6cc4c71cce9ab0c4bcfe63c619dd1e63f9ba02acae85"],"state_sha256":"28fb23282fafe63eb9daf880c1825e4405fd394174f2bcf0dc09b742b8e48580"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5k+gB17Ubjs+ELJbNbh7h0BVxogyJe/fOZdEVEaQXn2iVuvHE4shifsl4WN2UFn/8XDvE1ts/QtATKYIXGvSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:57:58.323458Z","bundle_sha256":"e717be7659f970a1d173261b8615cb062eb1b6e39856f8b99912290b7673c3c0"}}