{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:32BQSYPT5LUS5S673FIQ3BCHYY","short_pith_number":"pith:32BQSYPT","schema_version":"1.0","canonical_sha256":"de830961f3eae92ecbdfd9510d8447c60ed1b384e04d366f39bcb94822282f63","source":{"kind":"arxiv","id":"2110.12615","version":1},"attestation_state":"computed","paper":{"title":"Linear Contextual Bandits with Adversarial Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Quanquan Gu","submitted_at":"2021-10-25T02:53:24Z","abstract_excerpt":"We study the linear contextual bandit problem in the presence of adversarial corruption, where the interaction between the player and a possibly infinite decision set is contaminated by an adversary that can corrupt the reward up to a corruption level $C$ measured by the sum of the largest alteration on rewards in each round. We present a variance-aware algorithm that is adaptive to the level of adversarial contamination $C$. The key algorithmic design includes (1) a multi-level partition scheme of the observed data, (2) a cascade of confidence sets that are adaptive to the level of the corrup"},"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":"2110.12615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T02:53:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"02fb9a410e63f48430ff41af135b6c68a5d5966d34a2859e60bb68587fdcc1c4","abstract_canon_sha256":"eae185d351d4c46a85d32134cadd58d1953c32d6f88f81b1fe55704846d2dfb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:22.230452Z","signature_b64":"PPYw554xjL4llLmOoUm6yi7qR88pBQZn8/4ulUT7tYni66HNPUGML1/5xdmApz7JSZ9cQ5Dsp1bdlTg4d5iZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de830961f3eae92ecbdfd9510d8447c60ed1b384e04d366f39bcb94822282f63","last_reissued_at":"2026-07-05T03:25:22.230049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:22.230049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Contextual Bandits with Adversarial Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Quanquan Gu","submitted_at":"2021-10-25T02:53:24Z","abstract_excerpt":"We study the linear contextual bandit problem in the presence of adversarial corruption, where the interaction between the player and a possibly infinite decision set is contaminated by an adversary that can corrupt the reward up to a corruption level $C$ measured by the sum of the largest alteration on rewards in each round. We present a variance-aware algorithm that is adaptive to the level of adversarial contamination $C$. The key algorithmic design includes (1) a multi-level partition scheme of the observed data, (2) a cascade of confidence sets that are adaptive to the level of the corrup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12615","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/2110.12615/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":"2110.12615","created_at":"2026-07-05T03:25:22.230111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12615v1","created_at":"2026-07-05T03:25:22.230111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12615","created_at":"2026-07-05T03:25:22.230111+00:00"},{"alias_kind":"pith_short_12","alias_value":"32BQSYPT5LUS","created_at":"2026-07-05T03:25:22.230111+00:00"},{"alias_kind":"pith_short_16","alias_value":"32BQSYPT5LUS5S67","created_at":"2026-07-05T03:25:22.230111+00:00"},{"alias_kind":"pith_short_8","alias_value":"32BQSYPT","created_at":"2026-07-05T03:25:22.230111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08167","citing_title":"Multi-Agent Stochastic Bandits Robust to Adversarial Corruptions","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY","json":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY.json","graph_json":"https://pith.science/api/pith-number/32BQSYPT5LUS5S673FIQ3BCHYY/graph.json","events_json":"https://pith.science/api/pith-number/32BQSYPT5LUS5S673FIQ3BCHYY/events.json","paper":"https://pith.science/paper/32BQSYPT"},"agent_actions":{"view_html":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY","download_json":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY.json","view_paper":"https://pith.science/paper/32BQSYPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12615&json=true","fetch_graph":"https://pith.science/api/pith-number/32BQSYPT5LUS5S673FIQ3BCHYY/graph.json","fetch_events":"https://pith.science/api/pith-number/32BQSYPT5LUS5S673FIQ3BCHYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY/action/storage_attestation","attest_author":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY/action/author_attestation","sign_citation":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY/action/citation_signature","submit_replication":"https://pith.science/pith/32BQSYPT5LUS5S673FIQ3BCHYY/action/replication_record"}},"created_at":"2026-07-05T03:25:22.230111+00:00","updated_at":"2026-07-05T03:25:22.230111+00:00"}