{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RCRPA4VYZVLIAK4SNOO42HPE6O","short_pith_number":"pith:RCRPA4VY","schema_version":"1.0","canonical_sha256":"88a2f072b8cd56802b926b9dcd1de4f3b825b157b751e1acbd6d4241395a7995","source":{"kind":"arxiv","id":"2505.04608","version":4},"attestation_state":"computed","paper":{"title":"WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Drew Prinster, Suchi Saria, Xing Han","submitted_at":"2025-05-07T17:53:47Z","abstract_excerpt":"Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but also continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Methods for nonparametric sequential testing -- especially conformal test martingales (CTMs) and anytime-valid inference -- offer promising tools for this monitoring task. However, existing approaches are restricted to monitoring limited hypothesis classes or ``alarm criteria'' (e.g., detecting data shifts that violate certain exchangeab"},"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":"2505.04608","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:53:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2e75bec3877ca6b05461297d2af8e9f5d5821f4d1e412f34f29b257bf924fcea","abstract_canon_sha256":"caef55f3b475850861831b1b2d90daa29419303731038c76ad8b667de8543231"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:28.565027Z","signature_b64":"LBe7eY8Q/swfKiSWPIhHWPVUXXPUVkwkjzyCGl+goLstr2Mu4lk7CC3pbZA9yQOwHA2wBSlul2hAkQEOjfk/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88a2f072b8cd56802b926b9dcd1de4f3b825b157b751e1acbd6d4241395a7995","last_reissued_at":"2026-07-05T11:58:28.564294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:28.564294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Drew Prinster, Suchi Saria, Xing Han","submitted_at":"2025-05-07T17:53:47Z","abstract_excerpt":"Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but also continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Methods for nonparametric sequential testing -- especially conformal test martingales (CTMs) and anytime-valid inference -- offer promising tools for this monitoring task. However, existing approaches are restricted to monitoring limited hypothesis classes or ``alarm criteria'' (e.g., detecting data shifts that violate certain exchangeab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04608","kind":"arxiv","version":4},"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/2505.04608/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":"2505.04608","created_at":"2026-07-05T11:58:28.564381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04608v4","created_at":"2026-07-05T11:58:28.564381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04608","created_at":"2026-07-05T11:58:28.564381+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCRPA4VYZVLI","created_at":"2026-07-05T11:58:28.564381+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCRPA4VYZVLIAK4S","created_at":"2026-07-05T11:58:28.564381+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCRPA4VY","created_at":"2026-07-05T11:58:28.564381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11949","citing_title":"Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11949","citing_title":"Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15740","citing_title":"Evidence Sufficiency Under Delayed Ground Truth: Proxy Monitoring for Risk Decision Systems","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17836","citing_title":"Label-Free Detection of Governance Evidence Degradation in Risk Decision Systems","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O","json":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O.json","graph_json":"https://pith.science/api/pith-number/RCRPA4VYZVLIAK4SNOO42HPE6O/graph.json","events_json":"https://pith.science/api/pith-number/RCRPA4VYZVLIAK4SNOO42HPE6O/events.json","paper":"https://pith.science/paper/RCRPA4VY"},"agent_actions":{"view_html":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O","download_json":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O.json","view_paper":"https://pith.science/paper/RCRPA4VY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04608&json=true","fetch_graph":"https://pith.science/api/pith-number/RCRPA4VYZVLIAK4SNOO42HPE6O/graph.json","fetch_events":"https://pith.science/api/pith-number/RCRPA4VYZVLIAK4SNOO42HPE6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O/action/storage_attestation","attest_author":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O/action/author_attestation","sign_citation":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O/action/citation_signature","submit_replication":"https://pith.science/pith/RCRPA4VYZVLIAK4SNOO42HPE6O/action/replication_record"}},"created_at":"2026-07-05T11:58:28.564381+00:00","updated_at":"2026-07-05T11:58:28.564381+00:00"}