{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QABTJI6JB3LFMDWZH5EMYQYPZO","short_pith_number":"pith:QABTJI6J","schema_version":"1.0","canonical_sha256":"800334a3c90ed6560ed93f48cc430fcb88a2b427e4cdd56953072c1cfe6a59fb","source":{"kind":"arxiv","id":"2505.24097","version":1},"attestation_state":"computed","paper":{"title":"Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Baiting Chen, Qi Lei, Victor Li, Yuzhen Mao, Zhun Deng","submitted_at":"2025-05-30T00:59:25Z","abstract_excerpt":"Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a model so that its predictions satisfy explicit finite-sample statistical guarantees under a fixed, static, and unknown data-generating distribution. However, prediction-supported decisions may influence the outcome they aim to predict, a phenomenon named performativity of predictions, which is commonly seen in social science and economics. In this paper, we introduce Performative Risk Control, a framework to calibrate"},"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":"2505.24097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-30T00:59:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51f197ddae22e3b933d614ce7e0d4dac60b0f16b593a064838984beddf68fa79","abstract_canon_sha256":"349af0bf131da15dba97fd72104743cddb70d8c2b34a4127908ce3690fc9f5a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:41.787287Z","signature_b64":"d8vhczONZg9Eu5aY8QXq58HzveopEk+YZ9yLX+nNq2olD+scwyxXXvB/JWmcGnBioHBA5XUz9DAKc2O8GZ4VCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"800334a3c90ed6560ed93f48cc430fcb88a2b427e4cdd56953072c1cfe6a59fb","last_reissued_at":"2026-07-05T11:12:41.786770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:41.786770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Baiting Chen, Qi Lei, Victor Li, Yuzhen Mao, Zhun Deng","submitted_at":"2025-05-30T00:59:25Z","abstract_excerpt":"Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a model so that its predictions satisfy explicit finite-sample statistical guarantees under a fixed, static, and unknown data-generating distribution. However, prediction-supported decisions may influence the outcome they aim to predict, a phenomenon named performativity of predictions, which is commonly seen in social science and economics. In this paper, we introduce Performative Risk Control, a framework to calibrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24097","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/2505.24097/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":"2505.24097","created_at":"2026-07-05T11:12:41.786835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24097v1","created_at":"2026-07-05T11:12:41.786835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24097","created_at":"2026-07-05T11:12:41.786835+00:00"},{"alias_kind":"pith_short_12","alias_value":"QABTJI6JB3LF","created_at":"2026-07-05T11:12:41.786835+00:00"},{"alias_kind":"pith_short_16","alias_value":"QABTJI6JB3LFMDWZ","created_at":"2026-07-05T11:12:41.786835+00:00"},{"alias_kind":"pith_short_8","alias_value":"QABTJI6J","created_at":"2026-07-05T11:12:41.786835+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/QABTJI6JB3LFMDWZH5EMYQYPZO","json":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO.json","graph_json":"https://pith.science/api/pith-number/QABTJI6JB3LFMDWZH5EMYQYPZO/graph.json","events_json":"https://pith.science/api/pith-number/QABTJI6JB3LFMDWZH5EMYQYPZO/events.json","paper":"https://pith.science/paper/QABTJI6J"},"agent_actions":{"view_html":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO","download_json":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO.json","view_paper":"https://pith.science/paper/QABTJI6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24097&json=true","fetch_graph":"https://pith.science/api/pith-number/QABTJI6JB3LFMDWZH5EMYQYPZO/graph.json","fetch_events":"https://pith.science/api/pith-number/QABTJI6JB3LFMDWZH5EMYQYPZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO/action/storage_attestation","attest_author":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO/action/author_attestation","sign_citation":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO/action/citation_signature","submit_replication":"https://pith.science/pith/QABTJI6JB3LFMDWZH5EMYQYPZO/action/replication_record"}},"created_at":"2026-07-05T11:12:41.786835+00:00","updated_at":"2026-07-05T11:12:41.786835+00:00"}