{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AM3Z5XCOMBWI6EKB3BZ3JST6R5","short_pith_number":"pith:AM3Z5XCO","schema_version":"1.0","canonical_sha256":"03379edc4e606c8f1141d873b4ca7e8f5bc7fe99f28c73e73fb0fa658f36cb1e","source":{"kind":"arxiv","id":"2310.10461","version":3},"attestation_state":"computed","paper":{"title":"Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aodong Li, Chen Qiu, Clement Fung, Maja Rudolph","submitted_at":"2023-10-16T14:42:22Z","abstract_excerpt":"Anomaly detection is the task of identifying abnormal samples in large unlabeled datasets. While the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the absence of labeled validation data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors without labeled validation data. Instead of collecting labeled validation data, we generate synthetic anomalies wi"},"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":"2310.10461","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T14:42:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ddadac7837d54957f2dffa942db057c731ab52ff1ec9b105eb1b75fb629c6f32","abstract_canon_sha256":"4146f9cd0b2321b4122be622523cc6f1d95b5cc013edc7699689f8be8cce0750"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:25.012478Z","signature_b64":"33ZGhdUPMO7OF3RECYHOMBTJJWsKDatFgNGijwEAbs5QR4sQ+taYnq5oSiK1VSdU96FY4BE9wFZv4QQidmIKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03379edc4e606c8f1141d873b4ca7e8f5bc7fe99f28c73e73fb0fa658f36cb1e","last_reissued_at":"2026-07-05T09:07:25.011999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:25.011999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aodong Li, Chen Qiu, Clement Fung, Maja Rudolph","submitted_at":"2023-10-16T14:42:22Z","abstract_excerpt":"Anomaly detection is the task of identifying abnormal samples in large unlabeled datasets. While the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the absence of labeled validation data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors without labeled validation data. Instead of collecting labeled validation data, we generate synthetic anomalies wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10461","kind":"arxiv","version":3},"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/2310.10461/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":"2310.10461","created_at":"2026-07-05T09:07:25.012058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10461v3","created_at":"2026-07-05T09:07:25.012058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10461","created_at":"2026-07-05T09:07:25.012058+00:00"},{"alias_kind":"pith_short_12","alias_value":"AM3Z5XCOMBWI","created_at":"2026-07-05T09:07:25.012058+00:00"},{"alias_kind":"pith_short_16","alias_value":"AM3Z5XCOMBWI6EKB","created_at":"2026-07-05T09:07:25.012058+00:00"},{"alias_kind":"pith_short_8","alias_value":"AM3Z5XCO","created_at":"2026-07-05T09:07:25.012058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08742","citing_title":"AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20312","citing_title":"Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5","json":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5.json","graph_json":"https://pith.science/api/pith-number/AM3Z5XCOMBWI6EKB3BZ3JST6R5/graph.json","events_json":"https://pith.science/api/pith-number/AM3Z5XCOMBWI6EKB3BZ3JST6R5/events.json","paper":"https://pith.science/paper/AM3Z5XCO"},"agent_actions":{"view_html":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5","download_json":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5.json","view_paper":"https://pith.science/paper/AM3Z5XCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10461&json=true","fetch_graph":"https://pith.science/api/pith-number/AM3Z5XCOMBWI6EKB3BZ3JST6R5/graph.json","fetch_events":"https://pith.science/api/pith-number/AM3Z5XCOMBWI6EKB3BZ3JST6R5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5/action/storage_attestation","attest_author":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5/action/author_attestation","sign_citation":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5/action/citation_signature","submit_replication":"https://pith.science/pith/AM3Z5XCOMBWI6EKB3BZ3JST6R5/action/replication_record"}},"created_at":"2026-07-05T09:07:25.012058+00:00","updated_at":"2026-07-05T09:07:25.012058+00:00"}