{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DUVBLQLE44NB6C4G53PTKTHHS7","short_pith_number":"pith:DUVBLQLE","schema_version":"1.0","canonical_sha256":"1d2a15c164e71a1f0b86eedf354ce797c799f00ea71f0ce38bf37d75827ad1ef","source":{"kind":"arxiv","id":"2302.07832","version":2},"attestation_state":"computed","paper":{"title":"Deep Anomaly Detection under Labeling Budget Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aodong Li, Chen Qiu, Maja Rudolph, Marius Kloft, Padhraic Smyth, Stephan Mandt","submitted_at":"2023-02-15T18:18:35Z","abstract_excerpt":"Selecting informative data points for expert feedback can significantly improve the performance of anomaly detection (AD) in various contexts, such as medical diagnostics or fraud detection. In this paper, we determine a set of theoretical conditions under which anomaly scores generalize from labeled queries to unlabeled data. Motivated by these results, we propose a data labeling strategy with optimal data coverage under labeling budget constraints. In addition, we propose a new learning framework for semi-supervised AD. Extensive experiments on image, tabular, and video data sets show that o"},"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":"2302.07832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T18:18:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6201f64e33b2a44abaabb1edb1337c8467ca185c8b0f26b55bdb80c697685099","abstract_canon_sha256":"8a78ab2dcac31f6340185ac432cd14156131e60e81b6330b73567618f69c0a7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:46.012553Z","signature_b64":"FcwOe0nFJabcIoDqQXA+U6eAYLjNHvXWqvTEHPhtDSjkfgtCzGi8pBdWrruBfU3iINWP52jsiMYBDvzbsZZUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d2a15c164e71a1f0b86eedf354ce797c799f00ea71f0ce38bf37d75827ad1ef","last_reissued_at":"2026-07-05T06:27:46.012070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:46.012070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Anomaly Detection under Labeling Budget Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aodong Li, Chen Qiu, Maja Rudolph, Marius Kloft, Padhraic Smyth, Stephan Mandt","submitted_at":"2023-02-15T18:18:35Z","abstract_excerpt":"Selecting informative data points for expert feedback can significantly improve the performance of anomaly detection (AD) in various contexts, such as medical diagnostics or fraud detection. In this paper, we determine a set of theoretical conditions under which anomaly scores generalize from labeled queries to unlabeled data. Motivated by these results, we propose a data labeling strategy with optimal data coverage under labeling budget constraints. In addition, we propose a new learning framework for semi-supervised AD. Extensive experiments on image, tabular, and video data sets show that o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07832","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/2302.07832/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":"2302.07832","created_at":"2026-07-05T06:27:46.012133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07832v2","created_at":"2026-07-05T06:27:46.012133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07832","created_at":"2026-07-05T06:27:46.012133+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUVBLQLE44NB","created_at":"2026-07-05T06:27:46.012133+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUVBLQLE44NB6C4G","created_at":"2026-07-05T06:27:46.012133+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUVBLQLE","created_at":"2026-07-05T06:27:46.012133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01924","citing_title":"Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detection","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7","json":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7.json","graph_json":"https://pith.science/api/pith-number/DUVBLQLE44NB6C4G53PTKTHHS7/graph.json","events_json":"https://pith.science/api/pith-number/DUVBLQLE44NB6C4G53PTKTHHS7/events.json","paper":"https://pith.science/paper/DUVBLQLE"},"agent_actions":{"view_html":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7","download_json":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7.json","view_paper":"https://pith.science/paper/DUVBLQLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/DUVBLQLE44NB6C4G53PTKTHHS7/graph.json","fetch_events":"https://pith.science/api/pith-number/DUVBLQLE44NB6C4G53PTKTHHS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7/action/storage_attestation","attest_author":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7/action/author_attestation","sign_citation":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7/action/citation_signature","submit_replication":"https://pith.science/pith/DUVBLQLE44NB6C4G53PTKTHHS7/action/replication_record"}},"created_at":"2026-07-05T06:27:46.012133+00:00","updated_at":"2026-07-05T06:27:46.012133+00:00"}