{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PNXVKACPB37U772IORFSODGOOS","short_pith_number":"pith:PNXVKACP","schema_version":"1.0","canonical_sha256":"7b6f55004f0eff4fff48744b270cce7495fe52e6cd85950b4cc7d483eca5aad2","source":{"kind":"arxiv","id":"2606.09802","version":1},"attestation_state":"computed","paper":{"title":"Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debabrota Basu, Odalric-Ambrym Maillard, Udvas Das, Waris Radji","submitted_at":"2026-06-08T17:53:29Z","abstract_excerpt":"We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized preference vector, and in the presence of context distributions that are drifting over time. Under practitioner-friendly assumptions, we reduce this setting to linear bandit with stationary mean but heteroskedastic and non-stationary noise. We further study the case when the learner must ensure the mean reward of each decision must exceed that of a baseline strategy $\\boldsymbol{\\pi}_0$ at each decision step. We introduc"},"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":"2606.09802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:53:29Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1b60df9b5212eaad612349a9f88c5f67bb5e1681055176d8c2aaea522d7d0d1f","abstract_canon_sha256":"c138eecfc4e375ccda234a4999e1e873585feba9a27e9be3decaedfeb3fcf3b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:10.652217Z","signature_b64":"1Sd27nPX6Hj+yMzHX91UcuqpxT+DlOI8+B3xOH893ZkO+bqPwZeEgBHuEXd79UKLrrCYT6kkAJ4o01yGDPH3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6f55004f0eff4fff48744b270cce7495fe52e6cd85950b4cc7d483eca5aad2","last_reissued_at":"2026-06-09T02:09:10.651393Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:10.651393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Debabrota Basu, Odalric-Ambrym Maillard, Udvas Das, Waris Radji","submitted_at":"2026-06-08T17:53:29Z","abstract_excerpt":"We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized preference vector, and in the presence of context distributions that are drifting over time. Under practitioner-friendly assumptions, we reduce this setting to linear bandit with stationary mean but heteroskedastic and non-stationary noise. We further study the case when the learner must ensure the mean reward of each decision must exceed that of a baseline strategy $\\boldsymbol{\\pi}_0$ at each decision step. We introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09802","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/2606.09802/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":"2606.09802","created_at":"2026-06-09T02:09:10.651524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09802v1","created_at":"2026-06-09T02:09:10.651524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09802","created_at":"2026-06-09T02:09:10.651524+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNXVKACPB37U","created_at":"2026-06-09T02:09:10.651524+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNXVKACPB37U772I","created_at":"2026-06-09T02:09:10.651524+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNXVKACP","created_at":"2026-06-09T02:09:10.651524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS","json":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS.json","graph_json":"https://pith.science/api/pith-number/PNXVKACPB37U772IORFSODGOOS/graph.json","events_json":"https://pith.science/api/pith-number/PNXVKACPB37U772IORFSODGOOS/events.json","paper":"https://pith.science/paper/PNXVKACP"},"agent_actions":{"view_html":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS","download_json":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS.json","view_paper":"https://pith.science/paper/PNXVKACP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09802&json=true","fetch_graph":"https://pith.science/api/pith-number/PNXVKACPB37U772IORFSODGOOS/graph.json","fetch_events":"https://pith.science/api/pith-number/PNXVKACPB37U772IORFSODGOOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS/action/storage_attestation","attest_author":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS/action/author_attestation","sign_citation":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS/action/citation_signature","submit_replication":"https://pith.science/pith/PNXVKACPB37U772IORFSODGOOS/action/replication_record"}},"created_at":"2026-06-09T02:09:10.651524+00:00","updated_at":"2026-06-09T02:09:10.651524+00:00"}