{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VAFDMNAL3AEY3ZZ45VSBWEKWGA","short_pith_number":"pith:VAFDMNAL","schema_version":"1.0","canonical_sha256":"a80a36340bd8098de73ced641b1156301f99e19a0285866a4f7acb9957a8e9fd","source":{"kind":"arxiv","id":"2401.03756","version":4},"attestation_state":"computed","paper":{"title":"Adaptive Experimental Design for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","econ.EM","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kyohei Okumura, Masahiro Kato, Takuya Ishihara, Toru Kitagawa","submitted_at":"2024-01-08T09:29:07Z","abstract_excerpt":"This study investigates the contextual best arm identification (BAI) problem, aiming to design an adaptive experiment to identify the best treatment arm conditioned on contextual information (covariates). We consider a decision-maker who assigns treatment arms to experimental units during an experiment and recommends the estimated best treatment arm based on the contexts at the end of the experiment. The decision-maker uses a policy for recommendations, which is a function that provides the estimated best treatment arm given the contexts. In our evaluation, we focus on the worst-case expected "},"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":"2401.03756","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T09:29:07Z","cross_cats_sorted":["cs.AI","econ.EM","stat.ME","stat.ML"],"title_canon_sha256":"78248ddc35087ffdfb6ba7d366f160d2f13f5f7ba6da85f789aa36a217c1927b","abstract_canon_sha256":"c3f0ce444f264a054440675b7d654a199e2784c6e5e2c7b9481bc9a472eea6b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:02.234743Z","signature_b64":"wQllaQ6Cas7/peXF+A2Cg3optmo0mS2yZHMmchMRBAQXMnSPhxLyIHU1OxKm+7BA0A9JetgtOYybyhfLnT9UCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a80a36340bd8098de73ced641b1156301f99e19a0285866a4f7acb9957a8e9fd","last_reissued_at":"2026-07-05T11:24:02.234230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:02.234230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Experimental Design for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","econ.EM","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kyohei Okumura, Masahiro Kato, Takuya Ishihara, Toru Kitagawa","submitted_at":"2024-01-08T09:29:07Z","abstract_excerpt":"This study investigates the contextual best arm identification (BAI) problem, aiming to design an adaptive experiment to identify the best treatment arm conditioned on contextual information (covariates). We consider a decision-maker who assigns treatment arms to experimental units during an experiment and recommends the estimated best treatment arm based on the contexts at the end of the experiment. The decision-maker uses a policy for recommendations, which is a function that provides the estimated best treatment arm given the contexts. In our evaluation, we focus on the worst-case expected "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03756","kind":"arxiv","version":4},"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/2401.03756/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":"2401.03756","created_at":"2026-07-05T11:24:02.234293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03756v4","created_at":"2026-07-05T11:24:02.234293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03756","created_at":"2026-07-05T11:24:02.234293+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAFDMNAL3AEY","created_at":"2026-07-05T11:24:02.234293+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAFDMNAL3AEY3ZZ4","created_at":"2026-07-05T11:24:02.234293+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAFDMNAL","created_at":"2026-07-05T11:24:02.234293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20040","citing_title":"Active Context Selection Improves Simple Regret in Contextual Bandits","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA","json":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA.json","graph_json":"https://pith.science/api/pith-number/VAFDMNAL3AEY3ZZ45VSBWEKWGA/graph.json","events_json":"https://pith.science/api/pith-number/VAFDMNAL3AEY3ZZ45VSBWEKWGA/events.json","paper":"https://pith.science/paper/VAFDMNAL"},"agent_actions":{"view_html":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA","download_json":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA.json","view_paper":"https://pith.science/paper/VAFDMNAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03756&json=true","fetch_graph":"https://pith.science/api/pith-number/VAFDMNAL3AEY3ZZ45VSBWEKWGA/graph.json","fetch_events":"https://pith.science/api/pith-number/VAFDMNAL3AEY3ZZ45VSBWEKWGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA/action/storage_attestation","attest_author":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA/action/author_attestation","sign_citation":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA/action/citation_signature","submit_replication":"https://pith.science/pith/VAFDMNAL3AEY3ZZ45VSBWEKWGA/action/replication_record"}},"created_at":"2026-07-05T11:24:02.234293+00:00","updated_at":"2026-07-05T11:24:02.234293+00:00"}