{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OJZVTSSCM5WPHIEJN2MW4XFLCD","short_pith_number":"pith:OJZVTSSC","schema_version":"1.0","canonical_sha256":"727359ca42676cf3a0896e996e5cab10ddfb3fa28fd379da528a35f0c3448e5f","source":{"kind":"arxiv","id":"2506.07140","version":1},"attestation_state":"computed","paper":{"title":"Quantile-Optimal Policy Learning under Unmeasured Confounding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Siyu Chen, Xiaohong Chen, Zhengling Qi, Zhongren Chen, Zhuoran Yang","submitted_at":"2025-06-08T13:37:38Z","abstract_excerpt":"We study quantile-optimal policy learning where the goal is to find a policy whose reward distribution has the largest $\\alpha$-quantile for some $\\alpha \\in (0, 1)$. We focus on the offline setting whose generating process involves unobserved confounders. Such a problem suffers from three main challenges: (i) nonlinearity of the quantile objective as a functional of the reward distribution, (ii) unobserved confounding issue, and (iii) insufficient coverage of the offline dataset. To address these challenges, we propose a suite of causal-assisted policy learning methods that provably enjoy str"},"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":"2506.07140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-08T13:37:38Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"d5553a80a303c55671f2457621aae03804f4a41b79fac641d6db0593a40d4e6f","abstract_canon_sha256":"362ee7310958a7902bf1e0ea350423ccfa9312b23966b9131820eeafd6a52c63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:02.345937Z","signature_b64":"8VOnDujvtQ4wcaGEtG7ZkFUhNhHXmukqQf1EkO4dosF1vg3IipH7xizuiqfTYX68MyIY//bsLZYX7aj6E30fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"727359ca42676cf3a0896e996e5cab10ddfb3fa28fd379da528a35f0c3448e5f","last_reissued_at":"2026-07-05T11:18:02.345405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:02.345405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantile-Optimal Policy Learning under Unmeasured Confounding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Siyu Chen, Xiaohong Chen, Zhengling Qi, Zhongren Chen, Zhuoran Yang","submitted_at":"2025-06-08T13:37:38Z","abstract_excerpt":"We study quantile-optimal policy learning where the goal is to find a policy whose reward distribution has the largest $\\alpha$-quantile for some $\\alpha \\in (0, 1)$. We focus on the offline setting whose generating process involves unobserved confounders. Such a problem suffers from three main challenges: (i) nonlinearity of the quantile objective as a functional of the reward distribution, (ii) unobserved confounding issue, and (iii) insufficient coverage of the offline dataset. To address these challenges, we propose a suite of causal-assisted policy learning methods that provably enjoy str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07140","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/2506.07140/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":"2506.07140","created_at":"2026-07-05T11:18:02.345474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07140v1","created_at":"2026-07-05T11:18:02.345474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07140","created_at":"2026-07-05T11:18:02.345474+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJZVTSSCM5WP","created_at":"2026-07-05T11:18:02.345474+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJZVTSSCM5WPHIEJ","created_at":"2026-07-05T11:18:02.345474+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJZVTSSC","created_at":"2026-07-05T11:18:02.345474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09257","citing_title":"Regularity, Phase Transitions, and Uniform Inference for Proximal Counterfactual Quantile Processes","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD","json":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD.json","graph_json":"https://pith.science/api/pith-number/OJZVTSSCM5WPHIEJN2MW4XFLCD/graph.json","events_json":"https://pith.science/api/pith-number/OJZVTSSCM5WPHIEJN2MW4XFLCD/events.json","paper":"https://pith.science/paper/OJZVTSSC"},"agent_actions":{"view_html":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD","download_json":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD.json","view_paper":"https://pith.science/paper/OJZVTSSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07140&json=true","fetch_graph":"https://pith.science/api/pith-number/OJZVTSSCM5WPHIEJN2MW4XFLCD/graph.json","fetch_events":"https://pith.science/api/pith-number/OJZVTSSCM5WPHIEJN2MW4XFLCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD/action/storage_attestation","attest_author":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD/action/author_attestation","sign_citation":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD/action/citation_signature","submit_replication":"https://pith.science/pith/OJZVTSSCM5WPHIEJN2MW4XFLCD/action/replication_record"}},"created_at":"2026-07-05T11:18:02.345474+00:00","updated_at":"2026-07-05T11:18:02.345474+00:00"}