{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XSPM4HSL5W6XEB2JU53RETIUVU","short_pith_number":"pith:XSPM4HSL","schema_version":"1.0","canonical_sha256":"bc9ece1e4bedbd720749a777124d14ad06d01f23ff000f1ab8c20f0d3c240a8b","source":{"kind":"arxiv","id":"2504.10796","version":4},"attestation_state":"computed","paper":{"title":"Wasserstein Distributionally Robust Regret Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jose Blanchet, Lukas-Benedikt Fiechtner","submitted_at":"2025-04-15T01:47:11Z","abstract_excerpt":"Distributionally robust optimization (DRO) is widely used for decision-making under uncertainty, but its adversarial focus on worst-case loss can lead to overly conservative policies. To mitigate this, we study ex-ante Distributionally Robust Regret Optimization (DRRO) with Wasserstein ambiguity sets, designed to balance robustness with upside potential. We develop a theory of Wasserstein DRRO (WDRRO) paralleling Wasserstein DRO. Under smoothness and regularity, WDRRO selects among ERM optima by a first-order gradient-discrepancy rule. If the ERM optimizer is unique, first-order sensitivity va"},"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":"2504.10796","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-15T01:47:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5b78bef93d63598686c128dd09f8d91f85e97bfa12aa6cb6afc32d418e27d224","abstract_canon_sha256":"739ba60221317011f1df638d0782a640831581d4d2f2940e9c84bb1fbfbd8f7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:07.266659Z","signature_b64":"s2UlA0a18TsBfwIspMzcrzAvd3k8Z2eUHA9WmcNBeee6EXPttF0G2Eh36vf8DWk/SnNNAtW6kVUyz+orUMq1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc9ece1e4bedbd720749a777124d14ad06d01f23ff000f1ab8c20f0d3c240a8b","last_reissued_at":"2026-06-30T00:15:07.266170Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:07.266170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Distributionally Robust Regret Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jose Blanchet, Lukas-Benedikt Fiechtner","submitted_at":"2025-04-15T01:47:11Z","abstract_excerpt":"Distributionally robust optimization (DRO) is widely used for decision-making under uncertainty, but its adversarial focus on worst-case loss can lead to overly conservative policies. To mitigate this, we study ex-ante Distributionally Robust Regret Optimization (DRRO) with Wasserstein ambiguity sets, designed to balance robustness with upside potential. We develop a theory of Wasserstein DRRO (WDRRO) paralleling Wasserstein DRO. Under smoothness and regularity, WDRRO selects among ERM optima by a first-order gradient-discrepancy rule. If the ERM optimizer is unique, first-order sensitivity va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10796","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/2504.10796/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":"2504.10796","created_at":"2026-06-30T00:15:07.266226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10796v4","created_at":"2026-06-30T00:15:07.266226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10796","created_at":"2026-06-30T00:15:07.266226+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSPM4HSL5W6X","created_at":"2026-06-30T00:15:07.266226+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSPM4HSL5W6XEB2J","created_at":"2026-06-30T00:15:07.266226+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSPM4HSL","created_at":"2026-06-30T00:15:07.266226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.00155","citing_title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06158","citing_title":"Distributionally Robust Regret Optimal LQR with Common Stage-Law Ambiguity","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU","json":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU.json","graph_json":"https://pith.science/api/pith-number/XSPM4HSL5W6XEB2JU53RETIUVU/graph.json","events_json":"https://pith.science/api/pith-number/XSPM4HSL5W6XEB2JU53RETIUVU/events.json","paper":"https://pith.science/paper/XSPM4HSL"},"agent_actions":{"view_html":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU","download_json":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU.json","view_paper":"https://pith.science/paper/XSPM4HSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10796&json=true","fetch_graph":"https://pith.science/api/pith-number/XSPM4HSL5W6XEB2JU53RETIUVU/graph.json","fetch_events":"https://pith.science/api/pith-number/XSPM4HSL5W6XEB2JU53RETIUVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU/action/storage_attestation","attest_author":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU/action/author_attestation","sign_citation":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU/action/citation_signature","submit_replication":"https://pith.science/pith/XSPM4HSL5W6XEB2JU53RETIUVU/action/replication_record"}},"created_at":"2026-06-30T00:15:07.266226+00:00","updated_at":"2026-06-30T00:15:07.266226+00:00"}