{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LAFR53AYIQDGZS3TG5A5C3WYRG","short_pith_number":"pith:LAFR53AY","schema_version":"1.0","canonical_sha256":"580b1eec1844066ccb733741d16ed889926e7403696b908dbfe4563649b8a4ea","source":{"kind":"arxiv","id":"2602.02229","version":2},"attestation_state":"computed","paper":{"title":"Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Guanding Yu, Guangyi Zhang, Osvaldo Simeone, Yunlong Cai","submitted_at":"2026-02-02T15:32:14Z","abstract_excerpt":"We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a semi-supervised risk-monitoring approach based on prediction-powered inference (PPI). PPRM constructs anytime-valid lower bounds on the running risk by combining synthetic labels with a small set of true labels. Harmful shifts are detected via a threshold-based comparison with an upper bound on the nominal risk, satisfying assumption-free finite-sample guarantees on the type-I error. We demonstrate the effectiveness of"},"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":"2602.02229","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T15:32:14Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"bec722bb0de13ce041b0d4f9d3c567d318a09a734e982168bd134be041ea6eee","abstract_canon_sha256":"6e2479e6945f24bdce2cae51bc4888ff6a5301789b002a1a14400fcb9184bead"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:32.262392Z","signature_b64":"76DsW9UMmzPDKwP6Xw7gWNgCLRuXjsBKyQ0nSfBSxUSmPvdxNYq0vGvilmGjIrbFtOfWW4YhYc1+tW/Y5YWwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"580b1eec1844066ccb733741d16ed889926e7403696b908dbfe4563649b8a4ea","last_reissued_at":"2026-06-11T01:10:32.261348Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:32.261348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Guanding Yu, Guangyi Zhang, Osvaldo Simeone, Yunlong Cai","submitted_at":"2026-02-02T15:32:14Z","abstract_excerpt":"We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a semi-supervised risk-monitoring approach based on prediction-powered inference (PPI). PPRM constructs anytime-valid lower bounds on the running risk by combining synthetic labels with a small set of true labels. Harmful shifts are detected via a threshold-based comparison with an upper bound on the nominal risk, satisfying assumption-free finite-sample guarantees on the type-I error. We demonstrate the effectiveness of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02229","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/2602.02229/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":"2602.02229","created_at":"2026-06-11T01:10:32.261501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02229v2","created_at":"2026-06-11T01:10:32.261501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02229","created_at":"2026-06-11T01:10:32.261501+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAFR53AYIQDG","created_at":"2026-06-11T01:10:32.261501+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAFR53AYIQDGZS3T","created_at":"2026-06-11T01:10:32.261501+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAFR53AY","created_at":"2026-06-11T01:10:32.261501+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/LAFR53AYIQDGZS3TG5A5C3WYRG","json":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG.json","graph_json":"https://pith.science/api/pith-number/LAFR53AYIQDGZS3TG5A5C3WYRG/graph.json","events_json":"https://pith.science/api/pith-number/LAFR53AYIQDGZS3TG5A5C3WYRG/events.json","paper":"https://pith.science/paper/LAFR53AY"},"agent_actions":{"view_html":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG","download_json":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG.json","view_paper":"https://pith.science/paper/LAFR53AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02229&json=true","fetch_graph":"https://pith.science/api/pith-number/LAFR53AYIQDGZS3TG5A5C3WYRG/graph.json","fetch_events":"https://pith.science/api/pith-number/LAFR53AYIQDGZS3TG5A5C3WYRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG/action/storage_attestation","attest_author":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG/action/author_attestation","sign_citation":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG/action/citation_signature","submit_replication":"https://pith.science/pith/LAFR53AYIQDGZS3TG5A5C3WYRG/action/replication_record"}},"created_at":"2026-06-11T01:10:32.261501+00:00","updated_at":"2026-06-11T01:10:32.261501+00:00"}