{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QAPBVY3ASRBJFODTFQ5RK55HPF","short_pith_number":"pith:QAPBVY3A","schema_version":"1.0","canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","source":{"kind":"arxiv","id":"2410.08537","version":1},"attestation_state":"computed","paper":{"title":"Robust Offline Policy Learning with Observational Data from Multiple Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Gael Carranza, Susan Athey","submitted_at":"2024-10-11T05:16:23Z","abstract_excerpt":"We consider the problem of using observational bandit feedback data from multiple heterogeneous data sources to learn a personalized decision policy that robustly generalizes across diverse target settings. To achieve this, we propose a minimax regret optimization objective to ensure uniformly low regret under general mixtures of the source distributions. We develop a policy learning algorithm tailored to this objective, combining doubly robust offline policy evaluation techniques and no-regret learning algorithms for minimax optimization. Our regret analysis shows that this approach achieves "},"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":"2410.08537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T05:16:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3d1303fa2871cb437503230a96b77fe4849ae6b374883096ca54bf108fdd09f4","abstract_canon_sha256":"5b3e9bab9344b70308613f0d3fca30d74879037f7c4d21ce1c5c4dcf45867cda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:13.729983Z","signature_b64":"S21XkdbvdXP2YlkfNvrWisQORxP6vaIFFxgOMQrdROrj8dgpgqcvlJi8JzrF0WYsehNG5Eqr3PnQa7ydpDuQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","last_reissued_at":"2026-07-05T09:19:13.729492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:13.729492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Offline Policy Learning with Observational Data from Multiple Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Gael Carranza, Susan Athey","submitted_at":"2024-10-11T05:16:23Z","abstract_excerpt":"We consider the problem of using observational bandit feedback data from multiple heterogeneous data sources to learn a personalized decision policy that robustly generalizes across diverse target settings. To achieve this, we propose a minimax regret optimization objective to ensure uniformly low regret under general mixtures of the source distributions. We develop a policy learning algorithm tailored to this objective, combining doubly robust offline policy evaluation techniques and no-regret learning algorithms for minimax optimization. Our regret analysis shows that this approach achieves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08537","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/2410.08537/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":"2410.08537","created_at":"2026-07-05T09:19:13.729553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08537v1","created_at":"2026-07-05T09:19:13.729553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08537","created_at":"2026-07-05T09:19:13.729553+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAPBVY3ASRBJ","created_at":"2026-07-05T09:19:13.729553+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAPBVY3ASRBJFODT","created_at":"2026-07-05T09:19:13.729553+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAPBVY3A","created_at":"2026-07-05T09:19:13.729553+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.11136","citing_title":"Minimax Regret Estimation for Generalizing Heterogeneous Treatment Effects with Multisite Data","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF","json":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF.json","graph_json":"https://pith.science/api/pith-number/QAPBVY3ASRBJFODTFQ5RK55HPF/graph.json","events_json":"https://pith.science/api/pith-number/QAPBVY3ASRBJFODTFQ5RK55HPF/events.json","paper":"https://pith.science/paper/QAPBVY3A"},"agent_actions":{"view_html":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF","download_json":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF.json","view_paper":"https://pith.science/paper/QAPBVY3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08537&json=true","fetch_graph":"https://pith.science/api/pith-number/QAPBVY3ASRBJFODTFQ5RK55HPF/graph.json","fetch_events":"https://pith.science/api/pith-number/QAPBVY3ASRBJFODTFQ5RK55HPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/action/storage_attestation","attest_author":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/action/author_attestation","sign_citation":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/action/citation_signature","submit_replication":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/action/replication_record"}},"created_at":"2026-07-05T09:19:13.729553+00:00","updated_at":"2026-07-05T09:19:13.729553+00:00"}