{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AK4R3COXEG7PTX2V7AXQP4KZTS","short_pith_number":"pith:AK4R3COX","schema_version":"1.0","canonical_sha256":"02b91d89d721bef9df55f82f07f1599c9c4a912134ff228ea23a571af7bb3a90","source":{"kind":"arxiv","id":"2606.19117","version":1},"attestation_state":"computed","paper":{"title":"Wasserstein Policy Learning for Distributional Outcomes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","stat.ML"],"primary_cat":"stat.ME","authors_text":"Cheuk Hang Leung, Qi Wu, Yiyan Huang, Zhiheng Zhang","submitted_at":"2026-06-17T14:31:53Z","abstract_excerpt":"Offline policy learning has received growing attention in causal inference. The primary objective is to learn a policy (individualized treatment rule) as a mapping from covariates to treatment that maximizes the empirical welfare defined as the mean of scalar-valued potential outcomes. In this paper, we study offline policy learning with distribution-valued outcomes, where each potential outcome is a probability measure on $\\mathbb{R}$ and the reward is defined through a utility functional applied to the Wasserstein barycenter of induced outcome distributions. We establish statistical guarante"},"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":"2606.19117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-06-17T14:31:53Z","cross_cats_sorted":["cs.LG","econ.EM","stat.ML"],"title_canon_sha256":"0ee1ab5d9786d96d0123d3843f0880f9e1600f2c8b6662921812ad9fcc2504ba","abstract_canon_sha256":"0f75cc8bf62c7d868a3376b36749eec3939081e4f452d96a139003e6512f78de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:57.076966Z","signature_b64":"/2a4MuydY+7KbzNsFv34pyHaHk7WZvE5GDI4p50WfyGoNdDEcSbBB2CQmj8qldf7+1OyNo14leEtzAyEllW8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b91d89d721bef9df55f82f07f1599c9c4a912134ff228ea23a571af7bb3a90","last_reissued_at":"2026-06-19T16:11:57.076576Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:57.076576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Policy Learning for Distributional Outcomes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","econ.EM","stat.ML"],"primary_cat":"stat.ME","authors_text":"Cheuk Hang Leung, Qi Wu, Yiyan Huang, Zhiheng Zhang","submitted_at":"2026-06-17T14:31:53Z","abstract_excerpt":"Offline policy learning has received growing attention in causal inference. The primary objective is to learn a policy (individualized treatment rule) as a mapping from covariates to treatment that maximizes the empirical welfare defined as the mean of scalar-valued potential outcomes. In this paper, we study offline policy learning with distribution-valued outcomes, where each potential outcome is a probability measure on $\\mathbb{R}$ and the reward is defined through a utility functional applied to the Wasserstein barycenter of induced outcome distributions. We establish statistical guarante"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19117","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/2606.19117/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":"2606.19117","created_at":"2026-06-19T16:11:57.076639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19117v1","created_at":"2026-06-19T16:11:57.076639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19117","created_at":"2026-06-19T16:11:57.076639+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK4R3COXEG7P","created_at":"2026-06-19T16:11:57.076639+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK4R3COXEG7PTX2V","created_at":"2026-06-19T16:11:57.076639+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK4R3COX","created_at":"2026-06-19T16:11:57.076639+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/AK4R3COXEG7PTX2V7AXQP4KZTS","json":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS.json","graph_json":"https://pith.science/api/pith-number/AK4R3COXEG7PTX2V7AXQP4KZTS/graph.json","events_json":"https://pith.science/api/pith-number/AK4R3COXEG7PTX2V7AXQP4KZTS/events.json","paper":"https://pith.science/paper/AK4R3COX"},"agent_actions":{"view_html":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS","download_json":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS.json","view_paper":"https://pith.science/paper/AK4R3COX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19117&json=true","fetch_graph":"https://pith.science/api/pith-number/AK4R3COXEG7PTX2V7AXQP4KZTS/graph.json","fetch_events":"https://pith.science/api/pith-number/AK4R3COXEG7PTX2V7AXQP4KZTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS/action/storage_attestation","attest_author":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS/action/author_attestation","sign_citation":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS/action/citation_signature","submit_replication":"https://pith.science/pith/AK4R3COXEG7PTX2V7AXQP4KZTS/action/replication_record"}},"created_at":"2026-06-19T16:11:57.076639+00:00","updated_at":"2026-06-19T16:11:57.076639+00:00"}