{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OJZVTSSCM5WPHIEJN2MW4XFLCD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"362ee7310958a7902bf1e0ea350423ccfa9312b23966b9131820eeafd6a52c63","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-08T13:37:38Z","title_canon_sha256":"d5553a80a303c55671f2457621aae03804f4a41b79fac641d6db0593a40d4e6f"},"schema_version":"1.0","source":{"id":"2506.07140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07140","created_at":"2026-07-05T11:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07140v1","created_at":"2026-07-05T11:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07140","created_at":"2026-07-05T11:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"OJZVTSSCM5WP","created_at":"2026-07-05T11:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"OJZVTSSCM5WPHIEJ","created_at":"2026-07-05T11:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"OJZVTSSC","created_at":"2026-07-05T11:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:28c6b97441e19f1acbfac79a555181f836482031de340c4c68bd0e5369f12f82","target":"graph","created_at":"2026-07-05T11:18:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Siyu Chen, Xiaohong Chen, Zhengling Qi, Zhongren Chen, Zhuoran Yang","cross_cats":["cs.LG","econ.EM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-08T13:37:38Z","title":"Quantile-Optimal Policy Learning under Unmeasured Confounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07140","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ace75363f5afaceda293c432d479acf77545cc9bf22c595d62dd75a2089b26b4","target":"record","created_at":"2026-07-05T11:18:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"362ee7310958a7902bf1e0ea350423ccfa9312b23966b9131820eeafd6a52c63","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-08T13:37:38Z","title_canon_sha256":"d5553a80a303c55671f2457621aae03804f4a41b79fac641d6db0593a40d4e6f"},"schema_version":"1.0","source":{"id":"2506.07140","kind":"arxiv","version":1}},"canonical_sha256":"727359ca42676cf3a0896e996e5cab10ddfb3fa28fd379da528a35f0c3448e5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"727359ca42676cf3a0896e996e5cab10ddfb3fa28fd379da528a35f0c3448e5f","first_computed_at":"2026-07-05T11:18:02.345405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:02.345405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8VOnDujvtQ4wcaGEtG7ZkFUhNhHXmukqQf1EkO4dosF1vg3IipH7xizuiqfTYX68MyIY//bsLZYX7aj6E30fAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:02.345937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ace75363f5afaceda293c432d479acf77545cc9bf22c595d62dd75a2089b26b4","sha256:28c6b97441e19f1acbfac79a555181f836482031de340c4c68bd0e5369f12f82"],"state_sha256":"979ded25eab0d4d9104526b0135690652a4da1d2c6d3c0a00255ca96da1b6699"}