{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DFXNWPX3DV7UGSZRUIET44ZX2U","short_pith_number":"pith:DFXNWPX3","schema_version":"1.0","canonical_sha256":"196edb3efb1d7f434b31a2093e7337d53b09164c07a5daeee50d412a765a08cd","source":{"kind":"arxiv","id":"2506.16416","version":1},"attestation_state":"computed","paper":{"title":"On Continuous Monitoring of Risk Violations under Unknown Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Timans, Christian A. Naesseth, Eric Nalisnick, Rajeev Verma","submitted_at":"2025-06-19T15:52:24Z","abstract_excerpt":"Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assurances on the system's risk established beforehand. Common risk control frameworks rely on fixed assumptions and lack mechanisms to continuously monitor deployment reliability. In this work, we propose a general framework for the real-time monitoring of risk violations in evolving data streams. Leveraging the 'testing by betting' paradigm, we propose a sequential hypothesis testing procedure to detect violations of bo"},"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":"2506.16416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-19T15:52:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5b84cf669b4758a6ee18a9229733df607b2c5610f66b0d890515cf61598b757","abstract_canon_sha256":"ea3bf0ad6d78cb0659ad8e1bb5389e8a4dc0f08f6414a25b1bf044622ca786e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:36.153941Z","signature_b64":"tW7Y+QYKamOSB2WxIU5yTMXAr94cH2Qy/HMG0DlUJHb/E8ssDjiviR64Zr0VqP/d3LfWeUsF/wJu+aEZHXAKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"196edb3efb1d7f434b31a2093e7337d53b09164c07a5daeee50d412a765a08cd","last_reissued_at":"2026-07-05T11:24:36.153284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:36.153284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Continuous Monitoring of Risk Violations under Unknown Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Timans, Christian A. Naesseth, Eric Nalisnick, Rajeev Verma","submitted_at":"2025-06-19T15:52:24Z","abstract_excerpt":"Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assurances on the system's risk established beforehand. Common risk control frameworks rely on fixed assumptions and lack mechanisms to continuously monitor deployment reliability. In this work, we propose a general framework for the real-time monitoring of risk violations in evolving data streams. Leveraging the 'testing by betting' paradigm, we propose a sequential hypothesis testing procedure to detect violations of bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16416","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/2506.16416/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":"2506.16416","created_at":"2026-07-05T11:24:36.153371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16416v1","created_at":"2026-07-05T11:24:36.153371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16416","created_at":"2026-07-05T11:24:36.153371+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFXNWPX3DV7U","created_at":"2026-07-05T11:24:36.153371+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFXNWPX3DV7UGSZR","created_at":"2026-07-05T11:24:36.153371+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFXNWPX3","created_at":"2026-07-05T11:24:36.153371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02510","citing_title":"Online Safety Monitoring for LLMs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17836","citing_title":"Label-Free Detection of Governance Evidence Degradation in Risk Decision Systems","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U","json":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U.json","graph_json":"https://pith.science/api/pith-number/DFXNWPX3DV7UGSZRUIET44ZX2U/graph.json","events_json":"https://pith.science/api/pith-number/DFXNWPX3DV7UGSZRUIET44ZX2U/events.json","paper":"https://pith.science/paper/DFXNWPX3"},"agent_actions":{"view_html":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U","download_json":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U.json","view_paper":"https://pith.science/paper/DFXNWPX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16416&json=true","fetch_graph":"https://pith.science/api/pith-number/DFXNWPX3DV7UGSZRUIET44ZX2U/graph.json","fetch_events":"https://pith.science/api/pith-number/DFXNWPX3DV7UGSZRUIET44ZX2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U/action/storage_attestation","attest_author":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U/action/author_attestation","sign_citation":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U/action/citation_signature","submit_replication":"https://pith.science/pith/DFXNWPX3DV7UGSZRUIET44ZX2U/action/replication_record"}},"created_at":"2026-07-05T11:24:36.153371+00:00","updated_at":"2026-07-05T11:24:36.153371+00:00"}