{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7N3HBUVRBW7JIV4OBYN2OU7GQI","short_pith_number":"pith:7N3HBUVR","schema_version":"1.0","canonical_sha256":"fb7670d2b10dbe94578e0e1ba753e6823f7dfe7cb76773277f947c01b6f27e2e","source":{"kind":"arxiv","id":"2412.04346","version":2},"attestation_state":"computed","paper":{"title":"Distributionally Robust Performative Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Songkai Xue, Yuekai Sun","submitted_at":"2024-12-05T17:05:49Z","abstract_excerpt":"Performative prediction aims to model scenarios where predictive outcomes subsequently influence the very systems they target. The pursuit of a performative optimum (PO) -- minimizing performative risk -- is generally reliant on modeling of the distribution map, which characterizes how a deployed ML model alters the data distribution. Unfortunately, inevitable misspecification of the distribution map can lead to a poor approximation of the true PO. To address this issue, we introduce a novel framework of distributionally robust performative prediction and study a new solution concept termed as"},"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":"2412.04346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T17:05:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"56c561d03c62c37d7b3aba04c60e8948be8e4c8e90950048ce0cf1601173ee52","abstract_canon_sha256":"705d6859175e8bd0b602ceac460cf3d22363406979745a4da10943d7e6a26fbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:29.659545Z","signature_b64":"WpO5HK1MbefD/ZfXOE8Ztxs3mHlKUzDWP35u0ramY2/Kkn54T8Q/FiBZa2CUzTXQ4QvN8aw8yG6mC4WpSZsPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb7670d2b10dbe94578e0e1ba753e6823f7dfe7cb76773277f947c01b6f27e2e","last_reissued_at":"2026-07-05T10:11:29.658961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:29.658961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Performative Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Songkai Xue, Yuekai Sun","submitted_at":"2024-12-05T17:05:49Z","abstract_excerpt":"Performative prediction aims to model scenarios where predictive outcomes subsequently influence the very systems they target. The pursuit of a performative optimum (PO) -- minimizing performative risk -- is generally reliant on modeling of the distribution map, which characterizes how a deployed ML model alters the data distribution. Unfortunately, inevitable misspecification of the distribution map can lead to a poor approximation of the true PO. To address this issue, we introduce a novel framework of distributionally robust performative prediction and study a new solution concept termed as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04346","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/2412.04346/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":"2412.04346","created_at":"2026-07-05T10:11:29.659028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04346v2","created_at":"2026-07-05T10:11:29.659028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04346","created_at":"2026-07-05T10:11:29.659028+00:00"},{"alias_kind":"pith_short_12","alias_value":"7N3HBUVRBW7J","created_at":"2026-07-05T10:11:29.659028+00:00"},{"alias_kind":"pith_short_16","alias_value":"7N3HBUVRBW7JIV4O","created_at":"2026-07-05T10:11:29.659028+00:00"},{"alias_kind":"pith_short_8","alias_value":"7N3HBUVR","created_at":"2026-07-05T10:11:29.659028+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/7N3HBUVRBW7JIV4OBYN2OU7GQI","json":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI.json","graph_json":"https://pith.science/api/pith-number/7N3HBUVRBW7JIV4OBYN2OU7GQI/graph.json","events_json":"https://pith.science/api/pith-number/7N3HBUVRBW7JIV4OBYN2OU7GQI/events.json","paper":"https://pith.science/paper/7N3HBUVR"},"agent_actions":{"view_html":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI","download_json":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI.json","view_paper":"https://pith.science/paper/7N3HBUVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04346&json=true","fetch_graph":"https://pith.science/api/pith-number/7N3HBUVRBW7JIV4OBYN2OU7GQI/graph.json","fetch_events":"https://pith.science/api/pith-number/7N3HBUVRBW7JIV4OBYN2OU7GQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI/action/storage_attestation","attest_author":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI/action/author_attestation","sign_citation":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI/action/citation_signature","submit_replication":"https://pith.science/pith/7N3HBUVRBW7JIV4OBYN2OU7GQI/action/replication_record"}},"created_at":"2026-07-05T10:11:29.659028+00:00","updated_at":"2026-07-05T10:11:29.659028+00:00"}