{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SX2EC5UL37ZEOPRVSIGURR74D4","short_pith_number":"pith:SX2EC5UL","schema_version":"1.0","canonical_sha256":"95f441768bdff2473e35920d48c7fc1f174e667513da900d1f5a0fc53333d3b5","source":{"kind":"arxiv","id":"2311.13180","version":2},"attestation_state":"computed","paper":{"title":"Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chenlu Ye, Jianqing Fan, Zhaoran Wang, Zhuoran Yang","submitted_at":"2023-11-22T06:06:54Z","abstract_excerpt":"We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous batches and the rewards are revealed only at the end of the batch. Such a feedback structure is popular in applications such as personalized medicine and online advertisement, where the online data often do not arrive in a fully serial manner. We consider high-dimensional and linear settings where the reward function of the bandit model admits either a sparse o"},"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":"2311.13180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-22T06:06:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bcba966a8cad347c841804714baabbc87fb6550e14d81f21f6828350f0769915","abstract_canon_sha256":"95590c4a7ca70c458c001123c2c977cb9d62ba793e96a4ff15f680f1027e5f5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:04.960893Z","signature_b64":"05h+RptvZOf+5WkJT+6MYlBI85no/zgNB8Q8f/c7aMbWj33N66/R/uymyNpE7BI0RZ3n7xrQqDGhem3gFflfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f441768bdff2473e35920d48c7fc1f174e667513da900d1f5a0fc53333d3b5","last_reissued_at":"2026-07-05T07:16:04.960408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:04.960408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chenlu Ye, Jianqing Fan, Zhaoran Wang, Zhuoran Yang","submitted_at":"2023-11-22T06:06:54Z","abstract_excerpt":"We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous batches and the rewards are revealed only at the end of the batch. Such a feedback structure is popular in applications such as personalized medicine and online advertisement, where the online data often do not arrive in a fully serial manner. We consider high-dimensional and linear settings where the reward function of the bandit model admits either a sparse o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13180","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/2311.13180/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":"2311.13180","created_at":"2026-07-05T07:16:04.960470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13180v2","created_at":"2026-07-05T07:16:04.960470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13180","created_at":"2026-07-05T07:16:04.960470+00:00"},{"alias_kind":"pith_short_12","alias_value":"SX2EC5UL37ZE","created_at":"2026-07-05T07:16:04.960470+00:00"},{"alias_kind":"pith_short_16","alias_value":"SX2EC5UL37ZEOPRV","created_at":"2026-07-05T07:16:04.960470+00:00"},{"alias_kind":"pith_short_8","alias_value":"SX2EC5UL","created_at":"2026-07-05T07:16:04.960470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01919","citing_title":"Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4","json":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4.json","graph_json":"https://pith.science/api/pith-number/SX2EC5UL37ZEOPRVSIGURR74D4/graph.json","events_json":"https://pith.science/api/pith-number/SX2EC5UL37ZEOPRVSIGURR74D4/events.json","paper":"https://pith.science/paper/SX2EC5UL"},"agent_actions":{"view_html":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4","download_json":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4.json","view_paper":"https://pith.science/paper/SX2EC5UL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13180&json=true","fetch_graph":"https://pith.science/api/pith-number/SX2EC5UL37ZEOPRVSIGURR74D4/graph.json","fetch_events":"https://pith.science/api/pith-number/SX2EC5UL37ZEOPRVSIGURR74D4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4/action/storage_attestation","attest_author":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4/action/author_attestation","sign_citation":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4/action/citation_signature","submit_replication":"https://pith.science/pith/SX2EC5UL37ZEOPRVSIGURR74D4/action/replication_record"}},"created_at":"2026-07-05T07:16:04.960470+00:00","updated_at":"2026-07-05T07:16:04.960470+00:00"}