{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4LWWZ7QILUMCWKCETN63TC2CXW","short_pith_number":"pith:4LWWZ7QI","schema_version":"1.0","canonical_sha256":"e2ed6cfe085d182b28449b7db98b42bd9f2d3ff6905b4ed9825735fd9a910f65","source":{"kind":"arxiv","id":"2504.08097","version":2},"attestation_state":"computed","paper":{"title":"Fast Online Distributionally Robust Optimization via Data Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bartolomeo Stellato, Irina Wang, Marta Fochesato","submitted_at":"2025-04-10T19:48:50Z","abstract_excerpt":"We propose an online data compression approach for efficiently solving distributionally robust optimization (DRO) problems with streaming data while maintaining out-of-sample performance guarantees. Our method dynamically constructs ambiguity sets using online clustering, allowing the clustered configuration to evolve over time for an accurate representation of the underlying distribution. We establish theoretical conditions for clustering algorithms to ensure robustness, and show that the performance gap between our online solution and the nominal DRO solution can be written in terms of the d"},"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":"2504.08097","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-10T19:48:50Z","cross_cats_sorted":[],"title_canon_sha256":"1a1617dd85aa4ddfc526457e0873c460f42c8133096c65bbb8e22c75a7d076e8","abstract_canon_sha256":"381904eaac29f6abca6bd4cf20143d5fb93799e5125cfaefd3834b1524f83815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:16.435275Z","signature_b64":"6+0GDeE3gugRfXsa3dGZlarxT5aUKZ0XXsmbI0KgkB8IkXjplYiODxXhizjpKoGI/jZ2VbEWBUebLzuZpcZGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2ed6cfe085d182b28449b7db98b42bd9f2d3ff6905b4ed9825735fd9a910f65","last_reissued_at":"2026-07-05T12:09:16.434776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:16.434776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Online Distributionally Robust Optimization via Data Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bartolomeo Stellato, Irina Wang, Marta Fochesato","submitted_at":"2025-04-10T19:48:50Z","abstract_excerpt":"We propose an online data compression approach for efficiently solving distributionally robust optimization (DRO) problems with streaming data while maintaining out-of-sample performance guarantees. Our method dynamically constructs ambiguity sets using online clustering, allowing the clustered configuration to evolve over time for an accurate representation of the underlying distribution. We establish theoretical conditions for clustering algorithms to ensure robustness, and show that the performance gap between our online solution and the nominal DRO solution can be written in terms of the d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08097","kind":"arxiv","version":2},"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/2504.08097/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":"2504.08097","created_at":"2026-07-05T12:09:16.434836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08097v2","created_at":"2026-07-05T12:09:16.434836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08097","created_at":"2026-07-05T12:09:16.434836+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LWWZ7QILUMC","created_at":"2026-07-05T12:09:16.434836+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LWWZ7QILUMCWKCE","created_at":"2026-07-05T12:09:16.434836+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LWWZ7QI","created_at":"2026-07-05T12:09:16.434836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03075","citing_title":"Oracle-Based Distributionally Robust Optimization under Optimal Transport Ambiguity Sets","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW","json":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW.json","graph_json":"https://pith.science/api/pith-number/4LWWZ7QILUMCWKCETN63TC2CXW/graph.json","events_json":"https://pith.science/api/pith-number/4LWWZ7QILUMCWKCETN63TC2CXW/events.json","paper":"https://pith.science/paper/4LWWZ7QI"},"agent_actions":{"view_html":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW","download_json":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW.json","view_paper":"https://pith.science/paper/4LWWZ7QI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08097&json=true","fetch_graph":"https://pith.science/api/pith-number/4LWWZ7QILUMCWKCETN63TC2CXW/graph.json","fetch_events":"https://pith.science/api/pith-number/4LWWZ7QILUMCWKCETN63TC2CXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW/action/storage_attestation","attest_author":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW/action/author_attestation","sign_citation":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW/action/citation_signature","submit_replication":"https://pith.science/pith/4LWWZ7QILUMCWKCETN63TC2CXW/action/replication_record"}},"created_at":"2026-07-05T12:09:16.434836+00:00","updated_at":"2026-07-05T12:09:16.434836+00:00"}