{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NRU7QQBONKGDOPLTOCZYCAVTR3","short_pith_number":"pith:NRU7QQBO","schema_version":"1.0","canonical_sha256":"6c69f8402e6a8c373d7370b38102b38ed25cc245e24d849d2b6df6e09c13e2f0","source":{"kind":"arxiv","id":"2602.10971","version":2},"attestation_state":"computed","paper":{"title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junghyun Lee, Sanghwa Kim, Se-Young Yun","submitted_at":"2026-02-11T16:01:06Z","abstract_excerpt":"We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes heteroskedastic linear bandits and logistic/Poisson bandits, in the presence of adversarial corruptions. We propose HCW-GLB-OMD, which consists of two components: an online mirror descent (OMD)-based estimator and Hessian-based confidence weights to achieve corruption robustness. This is computationally efficient in that it only requires ${O}(1)$ space and time complexity per iteration. Under the self-concordance assumption on the link function, we show a regret bound of $\\"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.10971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T16:01:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"30f55ded498781c097163282b7324bb777e02017b87da950eeddb0af9d6e5393","abstract_canon_sha256":"5c0df1148a7cf7811a82a58810ac05bc20c4298777517199cbfd033d6cee26a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.274257Z","signature_b64":"Qti3/lrhjPPthXLQWdmXbo2JFiu3zlUfwQaQTbEAl7vk/NNdMoLO2y/QFfI3dyZWA4fCMIdR+ptsRaTcgKrEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c69f8402e6a8c373d7370b38102b38ed25cc245e24d849d2b6df6e09c13e2f0","last_reissued_at":"2026-06-23T03:13:54.273859Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.273859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junghyun Lee, Sanghwa Kim, Se-Young Yun","submitted_at":"2026-02-11T16:01:06Z","abstract_excerpt":"We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes heteroskedastic linear bandits and logistic/Poisson bandits, in the presence of adversarial corruptions. We propose HCW-GLB-OMD, which consists of two components: an online mirror descent (OMD)-based estimator and Hessian-based confidence weights to achieve corruption robustness. This is computationally efficient in that it only requires ${O}(1)$ space and time complexity per iteration. Under the self-concordance assumption on the link function, we show a regret bound of $\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10971","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/2602.10971/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.10971","created_at":"2026-06-23T03:13:54.273916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10971v2","created_at":"2026-06-23T03:13:54.273916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10971","created_at":"2026-06-23T03:13:54.273916+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRU7QQBONKGD","created_at":"2026-06-23T03:13:54.273916+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRU7QQBONKGDOPLT","created_at":"2026-06-23T03:13:54.273916+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRU7QQBO","created_at":"2026-06-23T03:13:54.273916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.09802","citing_title":"Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3","json":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3.json","graph_json":"https://pith.science/api/pith-number/NRU7QQBONKGDOPLTOCZYCAVTR3/graph.json","events_json":"https://pith.science/api/pith-number/NRU7QQBONKGDOPLTOCZYCAVTR3/events.json","paper":"https://pith.science/paper/NRU7QQBO"},"agent_actions":{"view_html":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3","download_json":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3.json","view_paper":"https://pith.science/paper/NRU7QQBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10971&json=true","fetch_graph":"https://pith.science/api/pith-number/NRU7QQBONKGDOPLTOCZYCAVTR3/graph.json","fetch_events":"https://pith.science/api/pith-number/NRU7QQBONKGDOPLTOCZYCAVTR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3/action/storage_attestation","attest_author":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3/action/author_attestation","sign_citation":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3/action/citation_signature","submit_replication":"https://pith.science/pith/NRU7QQBONKGDOPLTOCZYCAVTR3/action/replication_record"}},"created_at":"2026-06-23T03:13:54.273916+00:00","updated_at":"2026-06-23T03:13:54.273916+00:00"}